© 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. 20-GEMMASCOPE-RES-131K
    11. 125249
    Prev
    Next
    INDEX
    Explanations

    textual elements that signify a change in topic or structure, particularly punctuation and specific formatting cues

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

    names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juge
    -0.32
    indd
    -0.32
    ordum
    -0.32
    RepeatedField
    -0.31
     culte
    -0.30
     chaud
    -0.29
     başladı
    -0.29
     procès
    -0.29
     гай
    -0.29
     Industrial
    -0.28
    POSITIVE LOGITS
     للاسماء
    0.73
     للمعارف
    0.69
     ujednoznacz
    0.62
    󠁿
    0.56
     nahilalakip
    0.56
     namens
    0.55
    rungsseite
    0.55
    GEBURTSDATUM
    0.53
     مرئيه
    0.51
    angliski
    0.51
    Activations Density 0.054%

    No Known Activations