© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 2580
    Prev
    Next
    INDEX
    Explanations

    locations and entities related to legal cases and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    TacToe
    -0.74
     peindre
    -0.73
     COAST
    -0.73
    Maritime
    -0.72
     Harbour
    -0.72
     pantai
    -0.69
     Estuary
    -0.67
    Coastal
    -0.66
     Offshore
    -0.66
     Maritime
    -0.66
    POSITIVE LOGITS
     Andes
    0.87
     Alpine
    0.87
     Wyoming
    0.86
     Utah
    0.84
     aspen
    0.79
    Utah
    0.79
     Boli
    0.78
     Boise
    0.77
    Wyoming
    0.77
     Mormons
    0.76
    Activations Density 1.273%

    No Known Activations