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. 63313
    Prev
    Next
    INDEX
    Explanations

    mentions of fragments and their management in programming contexts

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

    Fragment code contexts

    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
    stdc
    -0.46
    PostMapping
    -0.37
    StandardCharsets
    -0.36
    esModule
    -0.36
     MaterialApp
    -0.35
     propTypes
    -0.32
    modelBuilder
    -0.31
    rungsseite
    -0.31
     supply
    -0.30
    ResponseWriter
    -0.30
    POSITIVE LOGITS
    adaptiveStyles
    0.67
    routeProvider
    0.60
     Chwiliwch
    0.57
    fragment
    0.56
     linkovi
    0.55
    TypedDataSet
    0.55
    enfone
    0.54
    $_['
    0.51
    ragment
    0.51
     lenker
    0.51
    Activations Density 0.002%

    No Known Activations