© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 102205
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming-related declarations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Verg
    -0.38
    CRC
    -0.37
    Nº
    -0.37
     anest
    -0.35
    Còn
    -0.35
    Instant
    -0.34
    FIX
    -0.34
    $_
    -0.34
     Viro
    -0.34
    PROTOBUF
    -0.34
    POSITIVE LOGITS
    declarations
    4.19
     declarations
    1.94
    Declarations
    1.64
     Declarations
    1.63
     declaration
    1.52
    declaration
    1.51
     Declaration
    1.33
    Declaration
    1.33
     DECLARATION
    1.28
    declar
    1.20
    Activations Density 0.000%

    No Known Activations