© 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 EvalsExportsAPI 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. 81034
    Prev
    Next
    INDEX
    Explanations

    common phrases and expressions of personal experience and recommendation

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

    much of, may bend, protection of

    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
     Italijanski
    -0.89
    oa̍t
    -0.77
    uxxxx
    -0.74
     يتيمه
    -0.73
    hyrchwyd
    -0.69
     informée
    -0.66
    хьтан
    -0.66
     surla
    -0.65
     Paglinawan
    -0.62
     OMITBAD
    -0.61
    POSITIVE LOGITS
    migrationBuilder
    0.39
    TestingModule
    0.36
     auszu
    0.34
    AntiForgeryToken
    0.34
    ˏ
    0.33
     ſtand
    0.32
    
    0.32
     reconna
    0.32
    Kirk
    0.32
    Seleccion
    0.31
    Activations Density 1.984%

    No Known Activations