© 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. 66287
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and technical language associated with data processing and analysis

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

    increasing displacement, data inputs

    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
    fjspx
    -0.69
    EndContext
    -0.57
    featureID
    -0.52
    styleType
    -0.52
     DbSet
    -0.51
    PropertyChanging
    -0.50
     setTotal
    -0.50
     iNdEx
    -0.49
    󠁬
    -0.48
     समीक्षाओं
    -0.47
    POSITIVE LOGITS
    angliski
    0.36
     tartalomajánló
    0.32
    əl
    0.30
    tg
    0.29
    JoinTable
    0.29
    Viungo
    0.29
    Override
    0.29
    holung
    0.29
     honden
    0.29
    ypus
    0.28
    Activations Density 0.070%

    No Known Activations