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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15693
    Prev
    Next
    INDEX
    Explanations

    references to places or entities in Connecticut

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

    Connecticut, Conn, or CT

    np_acts-logits-general · gemini-2.0-flash

    Connecticut and associated locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ConstraintMaker
    -0.73
     ModelExpression
    -0.73
    IntoConstraints
    -0.62
     SwiftUI
    -0.62
     архивлан
    -0.58
    AccessorTable
    -0.57
    ValueStyle
    -0.57
     Maur
    -0.54
    VolleyError
    -0.53
     Flinders
    -0.53
    POSITIVE LOGITS
     Connecticut
    1.11
    Connecticut
    1.02
     CT
    1.01
     Hartford
    0.96
     Conn
    0.88
     Courant
    0.84
    Conn
    0.81
    CT
    0.80
     ct
    0.78
     Yale
    0.78
    Activations Density 0.160%

    No Known Activations