© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 2972
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and entities in a software context

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

    programming method calls

    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
     
    -0.34
    .
    -0.27
    ,
    -0.27
     do
    -0.23
     spread
    -0.23
     j
    -0.23
    :
    -0.23
     g
    -0.23
     “
    -0.22
    <
    -0.22
    POSITIVE LOGITS
     ब्रेकडाउन
    1.17
     queſta
    1.05
    lapsingToolbar
    1.03
    ロウィン
    1.01
    expandindo
    0.99
    ValueStyle
    0.97
     disambiguazione
    0.97
    ikusbot
    0.95
    verwijspagina
    0.94
     imagui
    0.93
    Activations Density 0.021%

    No Known Activations