© 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. 34854
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating actions or processes

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

    past tense scientific actions

    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
     pleaſure
    -0.45
     dizendo
    -0.44
     diciendo
    -0.44
     saying
    -0.43
     warnings
    -0.43
    Jaunes
    -0.42
    Externí
    -0.42
     politiques
    -0.41
     letting
    -0.41
     queima
    -0.41
    POSITIVE LOGITS
     evaluated
    0.76
     analysed
    0.73
     investigated
    0.73
     assessed
    0.72
     analyzed
    0.71
     examined
    0.71
     successfully
    0.66
     found
    0.66
     explored
    0.64
     observed
    0.62
    Activations Density 0.256%

    No Known Activations