© 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. 908
    Prev
    Next
    INDEX
    Explanations

    expressions related to spontaneity and time constraints in social situations

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

    spontaneous and ad-hoc

    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
     defaultstate
    -0.75
    ########.
    -0.68
    ContentLoaded
    -0.61
     pinulongan
    -0.60
     ✭✭
    -0.59
    SOUNDBITE
    -0.58
    TagMode
    -0.55
     Administrativna
    -0.54
    Diweddarwch
    -0.54
    :✨
    -0.54
    POSITIVE LOGITS
     impromptu
    1.91
     spontaneous
    1.87
     spontan
    1.73
     spontaneously
    1.69
     unplanned
    1.64
     spont
    1.61
     spontaneity
    1.58
     Spontaneous
    1.54
     sudden
    1.49
     espont
    1.48
    Activations Density 0.093%

    No Known Activations