© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 126798
    Prev
    Next
    INDEX
    Explanations

    the presence of checkboxes in the text

    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
    Revenir
    -0.47
     hers
    -0.45
    fiez
    -0.44
    ════
    -0.43
    ọi
    -0.43
     utafitiHapana
    -0.42
    hood
    -0.42
    Slf
    -0.42
    makeConstraints
    -0.42
    {{/
    -0.41
    POSITIVE LOGITS
    BrowserModule
    4.16
     BrowserModule
    3.03
     CommonModule
    1.16
    CommonModule
    1.00
     للاسماء
    0.95
    AnimationsModule
    0.81
    Personensuche
    0.73
     NgModule
    0.68
     AppModule
    0.66
    AppRoutingModule
    0.66
    Activations Density 0.000%

    No Known Activations