© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2585
    Prev
    Next
    INDEX
    Explanations

    terms and symbols related to mathematical functions and physical definitions in quantum mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.60
    ↵↵
    -0.51
    <h2>
    -0.50
    ↵↵↵
    -0.49
    </tr>
    -0.49
     against
    -0.46
     September
    -0.45
    &+
    -0.43
    ","+
    -0.43
    ↵↵↵↵↵
    -0.43
    POSITIVE LOGITS
     initComponents
    0.87
    zelfde
    0.71
     مشين
    0.71
    migrationBuilder
    0.70
     endforeach
    0.67
    ThroughAttribute
    0.67
    {~
    0.66
     colspan
    0.64
     GenerationType
    0.63
     zijne
    0.62
    Activations Density 0.007%

    No Known Activations