© 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. 9925
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors that convey positive or appealing qualities

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

    descriptive adjectives followed by conjunctions/prepositions

    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
     stället
    -0.36
    她們
    -0.35
    sidemargin
    -0.35
     istället
    -0.35
     cellspacing
    -0.35
    潢
    -0.33
     perfons
    -0.33
    wnież
    -0.32
     Theſe
    -0.31
    ieuses
    -0.30
    POSITIVE LOGITS
     Alone
    0.64
     Together
    0.64
     paired
    0.61
    Alone
    0.57
     wrapped
    0.57
     together
    0.57
     under
    0.56
    ThroughAttribute
    0.56
     when
    0.55
     standing
    0.55
    Activations Density 0.056%

    No Known Activations