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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 28
    Prev
    Next
    INDEX
    Explanations

    location and administrative division references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     الدولى
    -0.71
     Quito
    -0.69
     Caracas
    -0.68
     Bucharest
    -0.65
     Parthen
    -0.65
     Marac
    -0.63
     Bogota
    -0.63
    Norge
    -0.61
    urlopen
    -0.61
     Ljubljana
    -0.61
    POSITIVE LOGITS
     southern
    0.69
     northern
    0.68
     western
    0.68
     Counties
    0.67
     County
    0.66
     counties
    0.65
    ridgeshire
    0.65
     District
    0.65
     eastern
    0.64
    cestershire
    0.64
    Activations Density 0.473%

    No Known Activations