© 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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 754
    Prev
    Next
    INDEX
    Explanations

    code elements related to struct definitions and function declarations in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astéroïdes
    -0.56
    WebVitals
    -0.53
    LabelTagHelper
    -0.51
    ImageContext
    -0.51
     IndexError
    -0.50
     <>",
    -0.48
    TargetException
    -0.48
     Mexique
    -0.47
    原始内容存档于
    -0.47
     betweenstory
    -0.46
    POSITIVE LOGITS
     char
    0.98
    char
    0.90
    struct
    0.74
     struct
    0.73
    const
    0.71
     int
    0.68
    int
    0.68
    void
    0.66
     void
    0.63
     const
    0.61
    Activations Density 0.563%

    No Known Activations