© 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. 6482
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific indicator (denoted by a special token)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    AccessorTable
    -0.95
    DropTable
    -0.84
    fjspx
    -0.81
    SourceChecksum
    -0.77
    setVerticalGroup
    -0.76
    PerformLayout
    -0.75
    keyColumn
    -0.73
    invokeLater
    -0.70
    NameInMap
    -0.67
    ēju
    -0.65
    POSITIVE LOGITS
     lenker
    0.73
     armis
    0.49
     للمعارف
    0.48
     елның
    0.47
     Suomi
    0.47
     الرياضيه
    0.45
    </thead>
    0.45
    úrese
    0.44
     nonatomic
    0.44
    htä
    0.43
    Activations Density 0.044%

    No Known Activations