© 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. 39180
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and optimal values in various contexts

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

    maximum value

    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
     menor
    -0.60
     mínimos
    -0.60
    Lower
    -0.59
    Min
    -0.58
     mínima
    -0.58
    LOWER
    -0.58
     Minimum
    -0.57
     minimum
    -0.57
     mínimo
    -0.57
     minimal
    -0.57
    POSITIVE LOGITS
     maximum
    1.35
     max
    1.29
    max
    1.27
     maximized
    1.27
     maximize
    1.24
     highest
    1.23
     maximizing
    1.23
     maximale
    1.21
     maximal
    1.20
     maximization
    1.20
    Activations Density 0.107%

    No Known Activations