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. 5088
    Prev
    Next
    INDEX
    Explanations

    non-standard characters or formatting issues in the text

    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
    RetentionPolicy
    -0.75
    RepeatedField
    -0.73
     Pais
    -0.72
    AccessorTable
    -0.70
    =-=-=-=-
    -0.70
    WithMany
    -0.69
    makeConstraints
    -0.68
    udnio
    -0.68
    <%
    -0.68
    jší
    -0.67
    POSITIVE LOGITS
    .........
    1.07
    ooooo
    0.73
    ?????
    0.73
    Psalms
    0.69
    !!!!!
    0.65
     .....
    0.64
    ffffff
    0.63
    >>>>>
    0.63
    oooooo
    0.62
    AAA
    0.61
    Activations Density 0.586%

    No Known Activations