© 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. 6655
    Prev
    Next
    INDEX
    Explanations

    statistical or analytical results related to the effectiveness and reliability of methods or processes in scientific research

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

    successful, satisfactory results

    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
     bazen
    -0.50
    sometimes
    -0.50
     manchmal
    -0.50
     magari
    -0.49
     kadang
    -0.49
    AsUp
    -0.49
     talvez
    -0.49
     quizá
    -0.48
     sometimes
    -0.48
     Italijanski
    -0.48
    POSITIVE LOGITS
     satisfactory
    1.20
     satisfactorily
    1.09
     successfully
    1.07
     excellent
    1.04
     successful
    0.93
    atisfactory
    0.89
     excellently
    0.88
    excellent
    0.86
    successfully
    0.85
     satisfied
    0.85
    Activations Density 0.500%

    No Known Activations