© 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. 123269
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements in code documentation

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

    code headers and comments

    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
    +#+#
    -0.80
    Britannique
    -0.71
    ConstraintMaker
    -0.70
     мәкал
    -0.68
    GraphicsUnit
    -0.67
    ftagPool
    -0.66
    tagext
    -0.66
     Chwiliwch
    -0.65
    delwed
    -0.65
     BorderSide
    -0.65
    POSITIVE LOGITS
     autorytatywna
    0.36
    BeginInit
    0.32
     Logement
    0.32
     oubli
    0.32
     Palest
    0.29
     WP
    0.28
    unlikely
    0.27
    <thead>
    0.27
     celo
    0.27
    async
    0.27
    Activations Density 0.005%

    No Known Activations