© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35052
    Prev
    Next
    INDEX
    Explanations

    references to medical studies and hormonal effects

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

    known that, anecdotal reports, accomplished through

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Sec
    -0.31
     test
    -0.30
     Races
    -0.29
    nloa
    -0.28
     نفر
    -0.28
     die
    -0.28
     stole
    -0.28
     trays
    -0.25
     re
    -0.25
     ng
    -0.25
    POSITIVE LOGITS
     reaſon
    0.66
     itſelf
    0.65
     abſ
    0.63
     fubject
    0.62
     ſch
    0.60
     ſever
    0.60
     diſt
    0.59
    AsUp
    0.59
     purpoſe
    0.59
     Diſ
    0.59
    Activations Density 0.056%

    No Known Activations