© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14093
    Prev
    Next
    INDEX
    Explanations

    options and alternatives related to legal defenses and rights

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

    options available to

    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
    MessageTagHelper
    -0.76
    rrggbb
    -0.66
    utilisons
    -0.62
    +#+#
    -0.60
    تقاوى
    -0.56
    новништво
    -0.55
    tagHelperRunner
    -0.53
     ब्रेकडाउन
    -0.52
     cherchés
    -0.49
    MemoryWarning
    -0.47
    POSITIVE LOGITS
     available
    1.50
    available
    1.38
     Available
    1.33
    Available
    1.32
     AVAILABLE
    1.14
     disponible
    1.10
     доступ
    1.05
    AVAILABLE
    1.03
     disponibles
    1.02
     dostęp
    1.02
    Activations Density 0.134%

    No Known Activations