© 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. 42803
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal circumstances and decisions

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

    potential outcomes and concerns

    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
    配
    -0.35
     door
    -0.32
     Door
    -0.31
    retty
    -0.30
     Blend
    -0.30
     saja
    -0.29
     TVA
    -0.29
    ğe
    -0.29
     Gong
    -0.28
     service
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.65
     שוליים
    0.63
    ########.
    0.59
     للمعارف
    0.59
    afficheront
    0.59
    esModule
    0.57
    parsedMessage
    0.57
    Clik
    0.56
    writeFieldEnd
    0.55
     الحره
    0.54
    Activations Density 0.077%

    No Known Activations