© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10519
    Prev
    Next
    INDEX
    Explanations

    coding structures, particularly related to functions and data structures in programming languages

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    MigrationBuilder
    -0.60
     defaultstate
    -0.58
    ьаж
    -0.52
     $_"
    -0.52
     referenties
    -0.49
     protoimpl
    -0.45
     elif
    -0.44
     ivelany
    -0.43
    ParallelGroup
    -0.42
    UNGEN
    -0.42
    POSITIVE LOGITS
    AutoField
    0.46
    TableHead
    0.43
     ustal
    0.41
    Попис
    0.39
    EDEFAULT
    0.38
     جه
    0.36
    otka
    0.36
    GEBURTSDATUM
    0.36
     دام
    0.35
     נק
    0.35
    Activations Density 0.398%

    No Known Activations