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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-RES-16K
    6. 7971
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the word "wo"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cu
    -0.57
    db
    -0.53
    Type
    -0.52
    ed
    -0.51
    and
    -0.50
    for
    -0.50
    OL
    -0.50
    Chain
    -0.49
    1
    -0.49
    -->
    -0.49
    POSITIVE LOGITS
    ^(@
    0.88
    NUMX
    0.87
    xFFFFFF
    0.84
    %";
    0.76
    olesale
    0.76
     BrowserModule
    0.75
     Seeder
    0.75
    ญิง
    0.73
    moiselle
    0.73
    writeFieldEnd
    0.73
    Activations Density 0.190%

    No Known Activations