© 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. 21-GEMMASCOPE-RES-16K
    11. 13514
    Prev
    Next
    INDEX
    Explanations

    pieces of code or data annotations related to string and data type declarations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.75
    webElementXpaths
    -0.72
    حياته
    -0.72
    addGap
    -0.67
    ConstraintMaker
    -0.65
    ngdoc
    -0.65
    __":
    -0.64
    ArgumentParser
    -0.64
    __':
    -0.63
    ://$
    -0.62
    POSITIVE LOGITS
     gevo
    0.33
     doppio
    0.33
    ANEOUS
    0.32
    ähig
    0.32
     Hauteur
    0.31
     coleção
    0.30
    同じく
    0.30
     refe
    0.30
    これも
    0.29
    хьтан
    0.29
    Activations Density 0.288%

    No Known Activations