Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93691
    Prev
    Next
    INDEX
    Explanations

    instances of type declarations and associated action types in programming-related content

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

    javascript and code keywords

    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
    RTCK
    -0.46
     Савезне
    -0.45
    ⓧ
    -0.40
    elseif
    -0.40
    zionalità
    -0.40
    ying
    -0.39
     مرئيه
    -0.39
    lihood
    -0.39
    ":[{
    -0.39
    ziehungen
    -0.39
    POSITIVE LOGITS
     createSlice
    0.55
    StoryboardSegue
    0.54
    $_['
    0.50
    XmlAccessType
    0.49
    AndEndTag
    0.48
     jsPsych
    0.47
    
    0.47
    帖最后由
    0.46
    AnimationsModule
    0.45
     nahilalakip
    0.45
    Activations Density 0.000%

    No Known Activations