© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3638
    Prev
    Next
    INDEX
    Explanations

    technical elements and attributes in programming code

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

    Code, file names, identifiers

    np_acts-logits-general · gemini-2.0-flash

    Mr congruent subunits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.64
    ModelSerializer
    -0.63
     دیکھیے
    -0.60
     ब्रेकडाउन
    -0.60
    addContainerGap
    -0.60
    MigrationBuilder
    -0.60
    帖最后由
    -0.59
    ⤹
    -0.56
    interopRequire
    -0.56
    verifyException
    -0.55
    POSITIVE LOGITS
     sub
    0.47
     individual
    0.45
     Sub
    0.38
     themselves
    0.38
     additional
    0.36
    sub
    0.35
    themselves
    0.35
    individual
    0.35
    Sub
    0.35
     Individual
    0.35
    Activations Density 0.472%

    No Known Activations