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. 11-GEMMASCOPE-RES-16K
    6. 8308
    Prev
    Next
    INDEX
    Explanations

    references to weekends and specific days or events occurring on those weekends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ništvo
    -0.50
     grecque
    -0.43
     Keating
    -0.43
    HandlerContext
    -0.42
     asiática
    -0.42
     institucional
    -0.41
     Văn
    -0.41
    parametrize
    -0.41
     tute
    -0.41
     calef
    -0.40
    POSITIVE LOGITS
     weekend
    1.14
    Sunday
    1.12
     Sunday
    1.11
    weekend
    1.05
     SUNDAY
    1.03
     Weekend
    0.98
    Weekend
    0.98
    SUNDAY
    0.97
     sunday
    0.96
     Saturday
    0.95
    Activations Density 0.144%

    No Known Activations