© 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. 30-GEMMASCOPE-RES-16K
    11. 12422
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure elements in programming language contexts

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

    Code, filenames, or programming terms

    np_acts-logits-general · gemini-2.0-flash

    search space delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.82
    évaluateur
    -0.80
     ब्रेकडाउन
    -0.78
    MessageOf
    -0.78
    GTCX
    -0.76
     esternos
    -0.76
    ंदीखरीदारी
    -0.72
    دانشنامهٔ
    -0.71
     autorytatywna
    -0.70
     propOrder
    -0.69
    POSITIVE LOGITS
     REP
    0.40
    rep
    0.38
    REP
    0.36
    Rep
    0.36
     Stig
    0.34
    inv
    0.34
     rep
    0.34
    溢
    0.33
     Peabody
    0.33
    àn
    0.33
    Activations Density 0.466%

    No Known Activations