© 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. 31-GEMMASCOPE-RES-131K
    11. 71099
    Prev
    Next
    INDEX
    Explanations

    references to educational activities or methodologies

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

    instructional learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.35
     coloriage
    -0.34
     professeurs
    -0.30
    PRIVATE
    -0.30
     entender
    -0.29
    าสตร์
    -0.28
     trasparente
    -0.27
    าหลี
    -0.27
     plegable
    -0.27
     transparente
    -0.27
    POSITIVE LOGITS
     otomatig
    0.66
     LMS
    0.60
    adaptiveStyles
    0.60
     uLocal
    0.58
     Artic
    0.57
    LMS
    0.56
    Portail
    0.53
     Instructional
    0.53
     Condo
    0.53
    sizeCache
    0.52
    Activations Density 0.021%

    No Known Activations