© 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. 87919
    Prev
    Next
    INDEX
    Explanations

    concepts related to learning and developing skills, particularly in the context of dogs and mathematics

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

    skills and concepts

    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
     što
    -0.47
     wą
    -0.38
     оригіналу
    -0.35
     يتيمه
    -0.33
     régime
    -0.32
    sufficient
    -0.32
     prosím
    -0.31
     bedrijven
    -0.31
     maail
    -0.31
    regime
    -0.31
    POSITIVE LOGITS
     spatial
    0.66
     patience
    0.66
     coordination
    0.64
     imagination
    0.63
     creativity
    0.59
     vocabulary
    0.59
    Хьажоргаш
    0.58
    $_['
    0.57
     teamwork
    0.56
    ValueStyle
    0.56
    Activations Density 0.017%

    No Known Activations