© 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. 19679
    Prev
    Next
    INDEX
    Explanations

    discussions about improvement and progress in skill or performance

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

    improvement and progress

    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
    Зноскі
    -0.66
    httphttps
    -0.64
    \{\\
    -0.63
     nakalista
    -0.62
    featureID
    -0.61
    richTextPanel
    -0.57
    aarrggbb
    -0.56
    IntoConstraints
    -0.56
    principalColumn
    -0.56
     thiệu
    -0.55
    POSITIVE LOGITS
     improvement
    1.77
     improvements
    1.57
     progress
    1.57
     Improvement
    1.45
    improvement
    1.44
    Improvement
    1.44
     improved
    1.39
     progrès
    1.38
    improve
    1.35
     improve
    1.34
    Activations Density 0.084%

    No Known Activations