© 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 EvalsExportsinterp-engineNEWAPI 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. 32654
    Prev
    Next
    INDEX
    Explanations

    references to time and dates

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

    time ranges

    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
    InputTagHelper
    -0.35
     nuclé
    -0.35
    แท
    -0.34
     desar
    -0.33
     konkuren
    -0.32
     estrategias
    -0.32
     CURIAM
    -0.31
    Stiftung
    -0.31
    adaptiveStyles
    -0.30
    ">*
    -0.29
    POSITIVE LOGITS
     afternoon
    0.80
    afternoon
    0.69
     noDo
    0.68
     noon
    0.66
     evening
    0.66
    ConstraintMaker
    0.64
     midday
    0.64
     afternoons
    0.63
     hour
    0.63
    Afternoon
    0.62
    Activations Density 0.013%

    No Known Activations