© 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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4326
    Prev
    Next
    INDEX
    Explanations

    opening and closing brackets or parentheses in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::::::::::::::::
    -0.73
     plais
    -0.67
    hatenablog
    -0.65
     Púb
    -0.63
    nonumber
    -0.63
     jspb
    -0.62
     appuntamento
    -0.62
    WriteLiteral
    -0.61
     Constitucional
    -0.59
    Xna
    -0.59
    POSITIVE LOGITS
    ({
    3.51
    ({
    
    3.02
     ({
    2.58
    >({
    2.33
    ({'
    1.62
    ({"
    1.59
    [{
    1.58
    ={{
    1.56
    ={({
    1.55
    ({_
    1.54
    Activations Density 0.119%

    No Known Activations