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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 14122
    Prev
    Next
    INDEX
    Explanations

    references to method execution in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     cancer
    -0.31
     save
    -0.30
    4
    -0.30
     Kurtz
    -0.30
    Save
    -0.30
     Larkin
    -0.30
    Random
    -0.30
     cell
    -0.29
     پاسخ
    -0.29
    for
    -0.29
    POSITIVE LOGITS
    zzleHttp
    4.50
     MessageBoxIcon
    1.73
    NameInMap
    1.07
     للاسماء
    1.04
     AssemblyCulture
    1.04
    IsMutable
    0.97
    rungsseite
    0.92
     propOrder
    0.91
    principalColumn
    0.88
     ProtoMessage
    0.88
    Activations Density 0.000%

    No Known Activations