© 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. 11743
    Prev
    Next
    INDEX
    Explanations

    code and programming language elements, specifically related to the Java and C++ programming languages

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

    `, const, String, long

    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
    AddTagHelper
    -0.80
    Tikang
    -0.77
     nakalista
    -0.72
    endphp
    -0.71
    Xna
    -0.70
     ModelExpression
    -0.69
    AndEndTag
    -0.69
     consultato
    -0.69
    localctx
    -0.68
    enterOuterAlt
    -0.68
    POSITIVE LOGITS
    rektur
    0.39
    ,
    0.37
     or
    0.33
    marginVertical
    0.32
     financiero
    0.32
     previously
    0.32
     financeira
    0.32
    <eos>
    0.32
     einst
    0.31
    stoß
    0.31
    Activations Density 0.026%

    No Known Activations