© 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. 20-GEMMASCOPE-RES-131K
    11. 42730
    Prev
    Next
    INDEX
    Explanations

    significant terms related to legal and administrative processes

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

    perk or valuable player

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
     fieldNum
    -0.39
    LEncoder
    -0.37
    ")==
    -0.37
    IContainer
    -0.36
    Chham
    -0.34
    RTSC
    -0.34
    ')->
    -0.34
     *)(
    -0.31
    =='
    -0.31
    )++;
    -0.30
    POSITIVE LOGITS
    Życiorys
    0.61
    المناصب
    0.58
     AssemblyVersion
    0.53
    发表于
    0.53
    XmlAccessType
    0.52
    adaptiveStyles
    0.52
     carina
    0.51
     gravure
    0.50
    DataAnnotations
    0.49
    withOpacity
    0.49
    Activations Density 0.264%

    No Known Activations