© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 15275
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.63
    
    -0.61
    RenderAtEndOf
    -0.60
     незавершена
    -0.57
    findpost
    -0.55
     ***!
    -0.54
    Datuak
    -0.52
     препратки
    -0.52
    ViewImports
    -0.49
    ########.
    -0.49
    POSITIVE LOGITS
     Let
    1.03
     let
    0.98
    Let
    0.93
     suppose
    0.89
     consider
    0.86
     Suppose
    0.86
    Suppose
    0.83
     Consider
    0.80
     denote
    0.76
    Consider
    0.75
    Activations Density 1.715%

    No Known Activations