© 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. 31-GEMMASCOPE-RES-131K
    11. 18926
    Prev
    Next
    INDEX
    Explanations

    key actions and processes related to decision-making and adaptability

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

    to practice

    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
     olla
    -0.37
    StackNavigator
    -0.33
    Personensuche
    -0.32
     prevails
    -0.31
     Gle
    -0.31
    ->{
    -0.31
     ה
    -0.30
    imread
    -0.29
    PROMPT
    -0.29
    deal
    -0.29
    POSITIVE LOGITS
     își
    0.68
     CURIAM
    0.61
     sharpen
    0.59
     laſſen
    0.53
     queſta
    0.52
     scattata
    0.52
    把手
    0.52
     अपना
    0.51
     autorytatywna
    0.51
     adjust
    0.51
    Activations Density 0.162%

    No Known Activations