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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1260
    Prev
    Next
    INDEX
    Explanations

    tokens that represent empty or no significant content in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the beginning of sections or paragraphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    InputBorder
    -0.80
    mybatisplus
    -0.76
    disposing
    -0.71
    :+:
    -0.70
    发表于
    -0.70
     ComVisible
    -0.69
     unknownFields
    -0.69
    ruptedException
    -0.64
    Референце
    -0.63
    KommentareTeilen
    -0.62
    POSITIVE LOGITS
    <blockquote>
    1.33
    <h4>
    0.87
    <h1>
    0.85
    <h2>
    0.82
    <h3>
    0.81
    <em>
    0.80
    <i>
    0.80
    <b>
    0.79
    <h6>
    0.77
    <strong>
    0.76
    Activations Density 0.004%

    No Known Activations