© 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. 53969
    Prev
    Next
    INDEX
    Explanations

    variables and values in programming contexts

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

    describing structure and dimensions

    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
     Waray
    -0.93
    ConstraintMaker
    -0.83
     surla
    -0.81
    AddTagHelper
    -0.75
    AddHtmlAttribute
    -0.74
     NSCoder
    -0.74
    MigrationBuilder
    -0.71
     pinulongan
    -0.69
    ItemBackground
    -0.67
    SPJ
    -0.66
    POSITIVE LOGITS
     typically
    0.39
    ):=\
    0.35
    ()")
    0.34
     Ganze
    0.33
    ):=
    0.32
    transQ
    0.31
     gjerne
    0.29
    }:=\
    0.29
    })]
    0.29
    >`;
    0.28
    Activations Density 0.070%

    No Known Activations