© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 2394
    Prev
    Next
    INDEX
    Explanations

    occurrences of various programming symbols and syntax elements

    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
    ™
    -0.50
     
    -0.50
    ↵↵
    -0.50
    ?
    -0.49
    -
    -0.49
    )
    -0.48
     Audiodateien
    -0.47
     '-')
    -0.46
    3
    -0.45
    .
    -0.43
    POSITIVE LOGITS
     ThemeData
    0.97
    帖最后由
    0.95
     فريبيس
    0.93
    Rüyada
    0.93
    الدراسه
    0.92
     Roskov
    0.89
    IsMutable
    0.89
    mybatisplus
    0.86
     mergeFrom
    0.85
    Източници
    0.85
    Activations Density 0.109%

    No Known Activations