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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101704
    Prev
    Next
    INDEX
    Explanations

    code syntax related to conditional structures and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     Marín
    -0.37
    objPHPExcel
    -0.34
    utsches
    -0.34
     verwendeten
    -0.33
    niczka
    -0.31
    yelidikan
    -0.30
     TAMBÉM
    -0.30
     przeznac
    -0.30
     prox
    -0.30
     жур
    -0.30
    POSITIVE LOGITS
     ModelExpression
    0.64
    IsContent
    0.63
     jadx
    0.59
    RenderAtEndOf
    0.57
     mergeFrom
    0.54
    TestingModule
    0.53
     للمعارف
    0.51
     doInBackground
    0.50
    outSlope
    0.50
    posedge
    0.49
    Activations Density 0.007%

    No Known Activations