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. 2-GEMMASCOPE-RES-16K
    6. 6712
    Prev
    Next
    INDEX
    Explanations

    references to worship and its related symbols or icons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.65
     tramo
    -0.61
    랫
    -0.58
    github
    -0.55
    ThroughAttribute
    -0.54
    pulumi
    -0.54
     rarity
    -0.53
     Rare
    -0.52
    matmul
    -0.51
     Kinn
    -0.51
    POSITIVE LOGITS
    newArrayList
    0.75
    vdash
    0.72
     мәкал
    0.70
     Soledad
    0.69
     Paglinawan
    0.67
     AssemblyCulture
    0.67
     vectorielle
    0.66
    krishnan
    0.66
     Bourgoin
    0.65
    mployment
    0.65
    Activations Density 0.034%

    No Known Activations