© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13611
    Prev
    Next
    INDEX
    Explanations

    identifiers related to programming constructs and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleUrls
    -0.96
    TagMode
    -0.91
    Koordinaten
    -0.54
    ValueStyle
    -0.54
     وتسجيلات
    -0.50
    gawai
    -0.49
     confronti
    -0.47
     PublicKey
    -0.47
     StatelessWidget
    -0.46
    bootstrapcdn
    -0.46
    POSITIVE LOGITS
    addCriterion
    1.97
     noqa
    1.13
    PerformLayout
    1.02
    TypedDataSet
    1.01
    WireFormatLite
    0.98
    addPreferredGap
    0.94
    DataPropertyName
    0.75
    jgl
    0.68
    LikeLike
    0.68
    ftagPool
    0.67
    Activations Density 0.016%

    No Known Activations