© 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. 44272
    Prev
    Next
    INDEX
    Explanations

    occurrences of time zone indicators and their associated formatting

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

    tz.transition format

    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
     myſelf
    -0.70
     pleaſure
    -0.65
     raiſ
    -0.64
     deſt
    -0.61
     unſ
    -0.61
     lenker
    -0.61
     faſt
    -0.61
     diſt
    -0.60
    
    -0.60
    ſelf
    -0.60
    POSITIVE LOGITS
     toalha
    0.35
    forChild
    0.35
     faça
    0.31
     xícara
    0.31
     Serien
    0.31
    cinhas
    0.30
     oubli
    0.30
     fizer
    0.30
     Barrera
    0.29
    WebServlet
    0.29
    Activations Density 0.023%

    No Known Activations