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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15058
    Prev
    Next
    INDEX
    Explanations

    references to dates, months, and specific time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     March
    -0.98
    March
    -0.95
     MARCH
    -0.88
    MARCH
    -0.87
     February
    -0.85
     Valentine
    -0.84
    February
    -0.84
    FEBRUARY
    -0.83
     FEBRUARY
    -0.81
     sprung
    -0.78
    POSITIVE LOGITS
     August
    1.68
    August
    1.61
     Aug
    1.59
    Aug
    1.50
     AUGUST
    1.42
    AUGUST
    1.42
    august
    1.34
     agosto
    1.29
     août
    1.26
     august
    1.26
    Activations Density 0.212%

    No Known Activations