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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120271
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and activities within programming and biological contexts

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

    programming and biology terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.76
    ंदीखरीदारी
    -0.73
    Geplaatst
    -0.71
    <unused17>
    -0.69
    <unused43>
    -0.69
    <unused41>
    -0.69
    <unused74>
    -0.69
    <unused76>
    -0.69
    <unused16>
    -0.69
    <unused21>
    -0.69
    POSITIVE LOGITS
    WebElementEntity
    0.31
     InputDecoration
    0.30
    ioutil
    0.29
    quelize
    0.27
    yarnpkg
    0.26
    (_,
    0.25
    nonatomic
    0.25
     Bretaña
    0.25
    age
    0.24
     vasco
    0.23
    Activations Density 0.090%

    No Known Activations