© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 7258
    Prev
    Next
    INDEX
    Explanations

    method parameters and their definitions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    function parameters and their type annotations in code documentation and function signatures.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.67
    CloseOperation
    -0.62
     ब्रेकडाउन
    -0.61
     lateinit
    -0.57
    Tikang
    -0.56
    AccessorTable
    -0.55
    basicConfig
    -0.54
     AssemblyTitle
    -0.53
     therefore
    -0.52
     للاسماء
    -0.52
    POSITIVE LOGITS
     optional
    0.99
    optional
    0.90
     Optional
    0.81
     OPTIONAL
    0.79
    Optional
    0.79
    OPTIONAL
    0.79
     opcional
    0.78
    opcional
    0.78
     optionally
    0.75
    可选
    0.71
    Activations Density 0.191%

    No Known Activations