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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12893
    Prev
    Next
    INDEX
    Explanations

    references to specific times and events

    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
     Nights
    -0.76
     nights
    -0.74
    Nights
    -0.71
     nachts
    -0.68
     nightly
    -0.67
     nacht
    -0.66
     Nacht
    -0.66
    Night
    -0.65
     nocturne
    -0.65
     nuit
    -0.65
    POSITIVE LOGITS
     afternoon
    1.50
     lunch
    1.31
     noon
    1.31
     Afternoon
    1.21
     midday
    1.20
    afternoon
    1.20
     Lunch
    1.19
    Afternoon
    1.18
    lunch
    1.18
    Lunch
    1.15
    Activations Density 0.100%

    No Known Activations