© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 127253
    Prev
    Next
    INDEX
    Explanations

    assertions or claims about actions and their correctness in discussions

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

    programming languages and libraries

    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
     TAMBÉM
    -0.36
     tromper
    -0.32
     newOwner
    -0.30
     Sicht
    -0.30
     règlement
    -0.30
     incendie
    -0.29
     almendras
    -0.27
     pendientes
    -0.27
     acuerdo
    -0.27
     fær
    -0.26
    POSITIVE LOGITS
     propOrder
    0.82
    ConstraintMaker
    0.69
    setVerticalGroup
    0.60
     resourceCulture
    0.60
     wireType
    0.58
     NSCoder
    0.58
     вікі
    0.54
    ніципалі
    0.54
    Parcelize
    0.54
    ьаж
    0.52
    Activations Density 0.053%

    No Known Activations