© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38827
    Prev
    Next
    INDEX
    Explanations

    expressions related to matching or compatibility, particularly in the context of personal items or styles

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

    color keyed, matching

    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
     beweging
    -0.37
    ValueGeneration
    -0.36
     Italijanski
    -0.36
    shadowOpacity
    -0.35
    RenderAtEndOf
    -0.34
     spalle
    -0.33
     terecht
    -0.33
    mml
    -0.32
    তথ্যসূত্র
    -0.32
     Lenti
    -0.32
    POSITIVE LOGITS
     matching
    1.99
     Matching
    1.76
    matching
    1.69
    Matching
    1.68
     match
    1.63
     matched
    1.60
     MATCH
    1.55
     matches
    1.45
    match
    1.39
    matched
    1.37
    Activations Density 0.066%

    No Known Activations