© 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. 93319
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific scientific or technical terminology

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

    induced change identifying affected unusual replicates

    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
     للاسماء
    -0.89
    InjectAttribute
    -0.88
     ModelExpression
    -0.82
     noDo
    -0.81
    ConstraintMaker
    -0.81
     فريبيس
    -0.80
    Архівовано
    -0.80
     informée
    -0.78
    Personensuche
    -0.78
    transQ
    -0.75
    POSITIVE LOGITS
     softly
    0.32
     thus
    0.31
     he
    0.31
     nan
    0.31
     then
    0.30
     कृ
    0.29
     they
    0.28
    く
    0.28
     not
    0.28
    ługi
    0.28
    Activations Density 0.226%

    No Known Activations