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. 15-GEMMASCOPE-RES-16K
    6. 12813
    Prev
    Next
    INDEX
    Explanations

    medical terms related to respiratory health and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsonwebtoken
    -0.71
     препратки
    -0.69
    Etimología
    -0.55
    steamcommunity
    -0.55
    publicPath
    -0.53
     trajets
    -0.51
    Enllaços
    -0.51
    jws
    -0.49
    mopol
    -0.48
    SupportActionBar
    -0.47
    POSITIVE LOGITS
    VideoCapture
    0.72
    mybatisplus
    0.72
    Personensuche
    0.71
    Vidite
    0.64
    Hochspringen
    0.64
    fjspx
    0.64
    tagHelperRunner
    0.64
    FormTagHelper
    0.64
    GTCX
    0.63
     otomatig
    0.62
    Activations Density 5.832%

    No Known Activations