Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7298
    Prev
    Next
    INDEX
    Explanations

    code structures, especially those related to function calls and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    endregion
    -0.33
     side
    -0.33
    Читати
    -0.33
     
    -0.32
     حق
    -0.32
     Side
    -0.32
    ↵↵
    -0.31
    cite
    -0.31
     vo
    -0.31
     Online
    -0.30
    POSITIVE LOGITS
    ExtendWith
    0.72
     мәкал
    0.68
     raiſ
    0.62
    下载附件
    0.58
    ConstraintMaker
    0.57
     vœ
    0.55
     defaultstate
    0.54
    PropertyChanging
    0.54
    ſammen
    0.54
    =$?
    0.54
    Activations Density 0.346%

    No Known Activations