© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8666
    Prev
    Next
    INDEX
    Explanations

    patterns of alteration or modification

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

    sections with promotional or spammy content and structured formatting, such as product/gambling mentions, bullet lists, tables, and metric/change notations.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dymyr
    -0.55
    Cryptography
    -0.52
     MonoBehaviour
    -0.49
    SourceChecksum
    -0.47
    CYCLE
    -0.47
    <tfoot>
    -0.46
     ayudarte
    -0.45
    cycle
    -0.43
     MATTER
    -0.43
    WebVitals
    -0.41
    POSITIVE LOGITS
    httphttps
    0.69
     kasarigan
    0.63
    setViewportView
    0.62
     confronti
    0.62
    matchCondition
    0.61
     kaarangay
    0.59
    Искәрмәләр
    0.58
     lenker
    0.58
    =$?
    0.57
    ulgação
    0.55
    Activations Density 0.023%

    No Known Activations