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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 8335
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and data structures

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    code documentation and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ”—
    -1.20
    <strong>
    -1.10
    <eos>
    -0.99
    .’”
    -0.95
    <em>
    -0.94
    —”
    -0.92
    <b>
    -0.91
    ,”
    -0.87
    —“
    -0.86
    )”.
    -0.83
    POSITIVE LOGITS
     `
    0.87
    ↵
    0.87
     */
    0.82
     '
    0.79
     TODO
    0.78
    <unused62>
    0.76
     ->
    0.75
    <unused61>
    0.74
    <unused63>
    0.70
     FIXME
    0.69
    Activations Density 1.902%

    No Known Activations