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. 14921
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to health and disease mechanisms

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

    Tokens followed by parentheses

    np_acts-logits-general · gemini-2.0-flash

    parenthesized abbreviations

    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
     kasarigan
    -0.70
    tahui
    -0.64
    archiviato
    -0.64
    writeFieldEnd
    -0.64
     referenties
    -0.63
     contextLoads
    -0.56
     "");
    
    -0.55
    EndGlobalSection
    -0.55
    =$?
    -0.55
    Tikang
    -0.54
    POSITIVE LOGITS
     (
    3.31
    (
    1.89
    (
    1.89
     (“
    1.78
     ("
    1.76
     ($
    1.71
     ('
    1.65
     (‘
    1.63
     (
    1.58
     ((
    1.58
    Activations Density 5.083%

    No Known Activations