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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-131K
    6. 119440
    Prev
    Next
    INDEX
    Explanations

    programming comments and documentation styles

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

    programming comments and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lah
    -0.32
    hadapi
    -0.31
     feit
    -0.31
    noopener
    -0.29
    principalTable
    -0.29
     heller
    -0.29
    liga
    -0.29
     старости
    -0.29
    umumkan
    -0.29
     quarta
    -0.29
    POSITIVE LOGITS
    sizeCache
    0.66
     transfieras
    0.65
     JADX
    0.63
    Geplaatst
    0.60
    //
    0.56
    /***
    
    0.56
    migrationBuilder
    0.54
    ⏟
    0.54
    ApiModelProperty
    0.52
    Javadoc
    0.52
    Activations Density 0.046%

    No Known Activations