© 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. 22-GEMMASCOPE-RES-16K
    11. 3391
    Prev
    Next
    INDEX
    Explanations

    mentions of evidence and verification processes related to assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sein
    -0.38
    laim
    -0.35
    laze
    -0.35
    ZoneId
    -0.34
    RSpec
    -0.34
     Sein
    -0.33
     Za
    -0.33
     itulah
    -0.33
    lain
    -0.33
    herjee
    -0.32
    POSITIVE LOGITS
    aarrggbb
    0.78
    تقاوى
    0.75
     Мексичка
    0.65
    Географиясе
    0.63
    KommentareTeilen
    0.58
     informée
    0.58
    ftagPool
    0.57
     AssemblyCompany
    0.56
     autorytatywna
    0.55
     jspb
    0.54
    Activations Density 0.947%

    No Known Activations