© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-GEMMASCOPE-RES-131K
    11. 96592
    Prev
    Next
    INDEX
    Explanations

    references to specific religious or cultural observances and celebrations

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

    religious holidays and festivals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chinoise
    -0.38
    @[+][
    -0.38
     sahiptir
    -0.37
     betale
    -0.37
     haces
    -0.35
     صوتيه
    -0.35
     duele
    -0.35
     noin
    -0.34
     olev
    -0.34
     Jurí
    -0.32
    POSITIVE LOGITS
     Ramadan
    2.20
     Ramadhan
    1.39
     رمضان
    1.27
     Diwali
    0.88
     Passover
    0.85
     Eid
    0.85
     puasa
    0.80
    Eid
    0.76
     Lent
    0.75
     Halloween
    0.73
    Activations Density 0.002%

    No Known Activations