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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14685
    Prev
    Next
    INDEX
    Explanations

    code structure elements, especially related to definitions, declarations, and annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     
    -0.44
     Mass
    -0.41
    vi
    -0.41
    аль
    -0.39
    كو
    -0.38
     كورة
    -0.38
     Ka
    -0.38
     an
    -0.38
     wij
    -0.37
    jawab
    -0.36
    POSITIVE LOGITS
     String
    2.47
    String
    2.40
     string
    2.39
    string
    2.21
     strings
    2.00
     Strings
    1.88
     STRING
    1.88
    STRING
    1.82
    NSString
    1.79
    字符串
    1.72
    Activations Density 0.229%

    No Known Activations