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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105770
    Prev
    Next
    INDEX
    Explanations

    instances of lists or collections in code

    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
     pleaſure
    -0.44
    semantics
    -0.43
     ActionBar
    -0.43
     nghỉ
    -0.41
     ändå
    -0.41
    Ndr
    -0.40
     ſche
    -0.40
    </>
    
    -0.40
    ∓
    -0.39
    省市镇
    -0.39
    POSITIVE LOGITS
     [[
    0.78
    __(/*!
    0.77
    =[[
    0.69
    [[
    0.67
    ([[
    0.62
    ":[{
    0.61
     autorytatywna
    0.58
    Demikian
    0.58
     ((((
    0.58
    (((
    0.57
    Activations Density 0.002%

    No Known Activations