© 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. 31-GEMMASCOPE-RES-16K
    11. 5943
    Prev
    Next
    INDEX
    Explanations

    programming or code-related structures and terms

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

    function parameters and argument lists with associated type annotations.

    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
    новништво
    -0.39
    ')['
    -0.37
    どちらも
    -0.30
     dvi
    -0.29
    tanleria
    -0.28
     Ambas
    -0.28
    isPrime
    -0.27
    Jîn
    -0.27
    AsUp
    -0.27
     Both
    -0.27
    POSITIVE LOGITS
    AddRange
    0.87
    addAll
    0.85
    (...
    0.84
     ...
    0.69
    ,...
    0.69
     (...
    0.67
     implode
    0.66
    ConstraintMaker
    0.63
    destroyAll
    0.63
    implode
    0.63
    Activations Density 0.411%

    No Known Activations