© 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. 121943
    Prev
    Next
    INDEX
    Explanations

    instances of the main method in programming code

    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
    AddTagHelper
    -0.97
    ValueStyle
    -0.96
     يتيمه
    -0.78
    rungsseite
    -0.76
    arangay
    -0.75
     kaarangay
    -0.72
    évaluateur
    -0.71
     صوتيه
    -0.71
     ModelExpression
    -0.71
    ロウィン
    -0.70
    POSITIVE LOGITS
     Main
    0.28
    Main
    0.28
     dónde
    0.24
     kr
    0.24
    where
    0.23
     typelib
    0.23
    thebibliography
    0.22
    doctype
    0.21
    centralwidget
    0.21
      
    0.20
    Activations Density 0.004%

    No Known Activations