Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 708
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations and related numbers in text

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

    proper nouns and place names, particularly geographic locations and town/city names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HFILL
    -0.48
    DrawerToggle
    -0.48
    日閲覧
    -0.48
    archiviato
    -0.47
    UrlResolution
    -0.47
    RectangleBorder
    -0.47
    InputBorder
    -0.46
    ThroughAttribute
    -0.45
    GeoNames
    -0.44
    errHandler
    -0.43
    POSITIVE LOGITS
     Notre
    0.53
    khart
    0.49
     Niles
    0.49
    Notre
    0.48
    SharedDtor
    0.41
     Kalamazoo
    0.41
     Mic
    0.40
     Culver
    0.36
     Granger
    0.35
     Beatty
    0.35
    Activations Density 0.093%

    No Known Activations