© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6096
    Prev
    Next
    INDEX
    Explanations

    code structures and function declarations in programming language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Acc
    -0.39
     Schlu
    -0.39
     vuel
    -0.39
     Viss
    -0.38
     Avic
    -0.38
     Mok
    -0.38
    Jerome
    -0.38
    fig
    -0.38
    subsec
    -0.38
    Aven
    -0.37
    POSITIVE LOGITS
    RegressionTest
    0.82
    RenderAtEndOf
    0.68
    httphttps
    0.63
     GenerationType
    0.59
     HasFactory
    0.54
    ThroughAttribute
    0.54
    HasForeignKey
    0.50
     الرياضيه
    0.49
     ObjectParameter
    0.48
     HttpNotFound
    0.47
    Activations Density 0.157%

    No Known Activations