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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 110751
    Prev
    Next
    INDEX
    Explanations

    words related to definitions and grammatical classifications

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

    defining words

    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
    setVerticalGroup
    -0.68
     ModelRenderer
    -0.68
    featureID
    -0.67
    ViewFeatures
    -0.65
    AndEndTag
    -0.65
    addCriterion
    -0.65
    GEBURTSDATUM
    -0.63
    parsedMessage
    -0.61
    сылкі
    -0.60
     HasFactory
    -0.59
    POSITIVE LOGITS
     mal
    0.57
     words
    0.54
     word
    0.52
     fl
    0.49
     noun
    0.48
     synonyms
    0.48
     Words
    0.48
     terms
    0.48
     definitions
    0.48
     synonym
    0.47
    Activations Density 0.102%

    No Known Activations