© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 7744
    Prev
    Next
    INDEX
    Explanations

    closing braces and structured ending symbols in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Coordenadas
    -0.50
    stylers
    -0.49
    烯
    -0.48
    ⓧ
    -0.44
     LCM
    -0.43
     freg
    -0.43
    Duff
    -0.43
    րջ
    -0.43
    omni
    -0.42
    appspot
    -0.42
    POSITIVE LOGITS
    (!__
    0.89
    endregion
    0.89
     مشين
    0.81
    ArgsConstructor
    0.80
    MemoryWarning
    0.79
    setVerticalGroup
    0.77
    endphp
    0.77
    ValueGeneration
    0.76
    endpush
    0.76
    SourceChecksum
    0.76
    Activations Density 0.216%

    No Known Activations