© 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. 25-GEMMASCOPE-RES-16K
    11. 7324
    Prev
    Next
    INDEX
    Explanations

    code structure and programming language syntax, particularly around functions and definitions

    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
    RetentionPolicy
    -0.58
    ?,
    -0.54
     ?,
    -0.53
     ?.
    -0.47
    enumii
    -0.47
     ?',
    -0.45
     “.
    -0.45
    且
    -0.45
    หมือน
    -0.45
    ,?
    -0.45
    POSITIVE LOGITS
    以下是
    0.78
    endregion
    0.76
    ================
    0.75
     henvisninger
    0.73
     Helpers
    0.70
     Functions
    0.69
     End
    0.69
    FUNCTIONS
    0.68
     FUNCTIONS
    0.68
    ここから
    0.68
    Activations Density 0.534%

    No Known Activations