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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 32346
    Prev
    Next
    INDEX
    Explanations

    code syntax related to function calls and parameter passing

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

    code completion with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ChildScrollView
    -0.78
    GraphicsUnit
    -0.75
    protoimpl
    -0.70
     ModelExpression
    -0.69
    ImageContext
    -0.67
     Infórmanos
    -0.66
     betweenstory
    -0.64
    KommentareTeilen
    -0.64
     كومونز
    -0.63
     Wicidata
    -0.61
    POSITIVE LOGITS
     gustaría
    0.27
     виправивши
    0.26
     FIXED
    0.26
     sientes
    0.26
    FIXED
    0.26
     Added
    0.26
     HEN
    0.26
     hagas
    0.26
     sienten
    0.25
     Zweiten
    0.25
    Activations Density 0.004%

    No Known Activations