© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10961
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding syntax, especially those relevant to API calls and responses

    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
     مشين
    -0.44
    __(/*!
    -0.40
     Acceso
    -0.34
     unit
    -0.31
     fuel
    -0.30
     {?}
    -0.30
     customerId
    -0.30
     critics
    -0.30
     critica
    -0.29
    Revenir
    -0.29
    POSITIVE LOGITS
     Discord
    0.61
     المعيارى
    0.59
    discord
    0.59
    Discord
    0.58
     discord
    0.57
    MigrationBuilder
    0.55
    mobileqq
    0.54
    ########.
    0.54
    nestjs
    0.52
    bot
    0.51
    Activations Density 0.113%

    No Known Activations