© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14247
    Prev
    Next
    INDEX
    Explanations

    code segments related to methods and functions in programming contexts

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

    method signatures and function declarations in code.

    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
    évaluateur
    -0.52
    endphp
    -0.46
    RenderAtEndOf
    -0.44
     doInBackground
    -0.42
     const
    -0.38
    foreach
    -0.37
     nullptr
    -0.36
    ->___
    -0.36
    期刊论文
    -0.36
     pautas
    -0.36
    POSITIVE LOGITS
    final
    1.11
     final
    1.04
     String
    0.96
    String
    0.87
    boolean
    0.84
     boolean
    0.77
    int
    0.67
     long
    0.66
    long
    0.65
     int
    0.65
    Activations Density 0.288%

    No Known Activations