© 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. 15-GEMMASCOPE-RES-16K
    11. 8851
    Prev
    Next
    INDEX
    Explanations

    instances of the word "during" in various contexts related to time and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.64
    ’?
    -0.61
    ...');
    -0.58
    »?
    -0.58
     Rolf
    -0.58
    Rolf
    -0.56
    }");
    -0.56
    }?
    -0.55
     himſelf
    -0.55
     EconPapers
    -0.55
    POSITIVE LOGITS
     During
    1.05
     periods
    1.03
    during
    1.00
    During
    0.97
     during
    0.95
     DURING
    0.93
    durante
    0.89
    periods
    0.82
     Periods
    0.79
    Durante
    0.78
    Activations Density 0.123%

    No Known Activations