© 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. 16634
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical expressions and functions

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

    parenthetical expressions containing code or math notation

    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
    [toxicity=0]
    -0.40
    <h1>
    -0.40
    <?
    -0.35
     Савезне
    -0.35
    package
    -0.34
     kaarangay
    -0.33
    ⓧ
    -0.31
    据
    -0.31
    Ска
    -0.30
    čius
    -0.30
    POSITIVE LOGITS
     useAppContext
    0.80
     '\\;'
    0.74
    LookAnd
    0.73
    rrggbb
    0.71
     ModelExpression
    0.70
    ftagPool
    0.69
    ChildScrollView
    0.69
     صوتيه
    0.67
    aarrggbb
    0.66
    ſammen
    0.66
    Activations Density 0.339%

    No Known Activations