© 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. 9-GEMMASCOPE-RES-16K
    11. 13119
    Prev
    Next
    INDEX
    Explanations

    elements related to web development and dependencies

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

    Code related to Common Weakness Enumeration (CWE)

    np_acts-logits-general · gemini-2.0-flash

    CWE identifiers

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GIVEREF
    -0.97
    下载附件
    -0.85
     виправивши
    -0.83
    expandindo
    -0.75
    +#+#
    -0.73
     protoimpl
    -0.73
     estekak
    -0.72
     HttpNotFound
    -0.71
    djangoproject
    -0.70
    kwds
    -0.69
    POSITIVE LOGITS
     surla
    0.73
     betweenstory
    0.59
    yarnpkg
    0.54
    tagHelper
    0.49
     kasarigan
    0.47
     autorytatywna
    0.47
    FromArgb
    0.46
     hikariConfig
    0.46
    rrggbb
    0.46
    حياتها
    0.43
    Activations Density 0.278%

    No Known Activations