© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5243
    Prev
    Next
    INDEX
    Explanations

    terms related to biological data analysis and querying processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    BLAST query

    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
    Negative Logits
    enteri
    -0.32
     fuori
    -0.32
    webElementGuid
    -0.31
     scuro
    -0.31
    RequiresApi
    -0.31
     quedado
    -0.30
    zionale
    -0.30
     Meksiku
    -0.30
    inheritDoc
    -0.29
    minValue
    -0.29
    POSITIVE LOGITS
    volley
    3.08
    VolleyError
    1.70
     Volley
    1.61
    Volley
    1.60
     volley
    1.39
     Volleyball
    0.94
    Volleyball
    0.86
     volleyball
    0.86
    RequestQueue
    0.79
     OFDb
    0.77
    Activations Density 0.000%

    No Known Activations