© 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. 5069
    Prev
    Next
    INDEX
    Explanations

    structures related to code syntax, particularly focusing on program flow and block closures

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

    closing braces and curly brackets that end code blocks or method definitions.

    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
     MainAxisSize
    -0.56
    SharedCtor
    -0.56
     nakalista
    -0.55
    Bioaccumulative
    -0.55
    tangentMode
    -0.54
     intStringLen
    -0.54
     للمعارف
    -0.54
    ftagPool
    -0.54
    aarrggbb
    -0.52
    Pozri
    -0.51
    POSITIVE LOGITS
    能否
    0.42
    public
    0.40
    void
    0.39
     public
    0.39
    Override
    0.38
     Par
    0.38
    (){}
    0.37
     potest
    0.36
     Pub
    0.36
     Part
    0.36
    Activations Density 0.122%

    No Known Activations