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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6187
    Prev
    Next
    INDEX
    Explanations

    references to towns and related administrative divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Karlsruhe
    -0.70
     Schulte
    -0.70
     Warszawie
    -0.65
     MediatR
    -0.65
    BuilderFactory
    -0.63
    dicas
    -0.63
    λλ
    -0.61
    aviar
    -0.59
    kki
    -0.58
    tyczne
    -0.58
    POSITIVE LOGITS
     town
    3.02
     Town
    2.86
     TOWN
    2.74
    Town
    2.66
    town
    2.45
     towns
    2.37
    TOWN
    2.31
     Towns
    2.04
    towns
    2.02
    Towns
    1.91
    Activations Density 0.031%

    No Known Activations