© 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. 42470
    Prev
    Next
    INDEX
    Explanations

    statistical evaluations and outcomes related to treatment effects in studies

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

    statement of feasibility

    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
    principalColumn
    -0.46
    spesies
    -0.46
     للاسماء
    -0.43
     joyas
    -0.38
    audiovisuel
    -0.38
    PyExc
    -0.37
     autoridad
    -0.36
     JpaRepository
    -0.36
     Wahrheit
    -0.35
     pisang
    -0.34
    POSITIVE LOGITS
     otomatig
    0.66
     itſelf
    0.51
     فريبيس
    0.48
    twimg
    0.47
     autorytatywna
    0.47
    TIMORE
    0.46
    RepeatedField
    0.45
    felves
    0.45
     themſelves
    0.44
    AndEndTag
    0.43
    Activations Density 0.429%

    No Known Activations