© 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. 12207
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or emphasis in conversational language

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

    how, what, qué, 多少

    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
     tartalomajánló
    -0.46
     مشين
    -0.44
     }^{[
    -0.44
    なぜか
    -0.44
    TagHelpers
    -0.44
    </thead>
    -0.42
    <()>
    -0.41
     EconPapers
    -0.41
    expandindo
    -0.41
     bugged
    -0.41
    POSITIVE LOGITS
     how
    1.09
     what
    0.88
    多么
    0.87
     qué
    0.87
     چه
    0.84
     چقدر
    0.83
     कित
    0.83
    how
    0.83
     How
    0.82
    How
    0.77
    Activations Density 0.029%

    No Known Activations