Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8461
    Prev
    Next
    INDEX
    Explanations

    references to holidays and rituals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </tfoot>
    -0.40
    binary
    -0.38
    Binary
    -0.38
    ('''
    -0.38
     Christmas
    -0.37
    <table>
    -0.36
     Lovel
    -0.34
     phrase
    -0.33
    <h2>
    -0.33
     binary
    -0.33
    POSITIVE LOGITS
     holidays
    1.05
     holiday
    0.93
     Holidays
    0.91
    holidays
    0.90
    holiday
    0.90
    Holidays
    0.86
    Holiday
    0.73
     HOLIDAY
    0.71
    SequentialGroup
    0.70
     Holiday
    0.68
    Activations Density 0.046%

    No Known Activations