Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12773
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and references to personal experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences starting with "I" or "We"

    np_acts-logits-general · gemini-2.0-flash

    personal complaints and demands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.82
    Personendaten
    -0.70
     Wicidata
    -0.66
     Roskov
    -0.62
    OGND
    -0.62
     okuyayım
    -0.61
    帖最后由
    -0.59
     JAXBElement
    -0.58
    ViewFeatures
    -0.57
    ьаж
    -0.56
    POSITIVE LOGITS
     complained
    0.73
     demanded
    0.62
     filed
    0.61
     reported
    0.61
     requested
    0.60
     complaint
    0.57
     pleaded
    0.56
    Reported
    0.56
     complain
    0.56
    Complaint
    0.56
    Activations Density 0.225%

    No Known Activations