© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 121729
    Prev
    Next
    INDEX
    Explanations

    markup indicators and parameters within code or text

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

    code comments and structure

    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
     appro
    -0.36
     concreto
    -0.36
    isNaN
    -0.35
    amentlich
    -0.35
     histor
    -0.35
    tighets
    -0.34
     NaN
    -0.33
     sockaddr
    -0.33
    HtmlAttribute
    -0.32
     voilà
    -0.32
    POSITIVE LOGITS
    UnusedPrivate
    0.70
    httphttps
    0.66
     betweenstory
    0.65
    setVerticalGroup
    0.63
    LookAnd
    0.62
    RegressionTest
    0.61
    帖最后由
    0.60
    GraphicsUnit
    0.57
    IndentedString
    0.53
     Chwiliwch
    0.52
    Activations Density 0.018%

    No Known Activations