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. 9267
    Prev
    Next
    INDEX
    Explanations

    code structures and delimiters in programming syntax

    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
     continúas
    -0.60
    才會
    -0.50
     Mo
    -0.49
    LikeLike
    -0.49
    %@",
    -0.47
     chal
    -0.47
    JsonPropertyName
    -0.47
     CIT
    -0.47
     Ale
    -0.46
     extended
    -0.46
    POSITIVE LOGITS
    if
    0.87
     الحره
    0.72
    WebVitals
    0.72
    WriteTagHelper
    0.70
    SharedCtor
    0.70
     AssemblyCulture
    0.69
    memset
    0.68
     protoimpl
    0.67
    switch
    0.66
    存于互联网档案馆
    0.66
    Activations Density 0.149%

    No Known Activations