© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 118091
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names starting with "Dav" or variations of it

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

    names starting with Dav

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.49
    hasMoreElements
    -0.45
     Strickland
    -0.44
    DECREF
    -0.44
    ButterKnife
    -0.44
    省市镇
    -0.43
     ore
    -0.43
     OkHttpClient
    -0.43
     Ore
    -0.43
     Commune
    -0.42
    POSITIVE LOGITS
     Dav
    2.33
    Dav
    2.31
    dav
    2.22
    DAV
    1.98
     dav
    1.96
     DAV
    1.90
     Davids
    1.34
     Davison
    1.25
     Davido
    1.23
     Daven
    1.16
    Activations Density 0.003%

    No Known Activations