© 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. 25-GEMMASCOPE-RES-16K
    11. 4657
    Prev
    Next
    INDEX
    Explanations

    code constructs related to functions and methods, particularly those that are overridden or protected

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.72
    MigrationBuilder
    -0.68
    
    -0.66
    ]^{-
    -0.62
     ${
    -0.56
     CreateTagHelper
    -0.56
     kaarangay
    -0.55
    fören
    -0.53
     crossorigin
    -0.53
     AssemblyProduct
    -0.50
    POSITIVE LOGITS
    final
    0.98
    late
    0.96
    bool
    0.88
     final
    0.78
    void
    0.78
     late
    0.72
    Future
    0.69
    String
    0.67
     bool
    0.66
    var
    0.65
    Activations Density 0.051%

    No Known Activations