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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12418
    Prev
    Next
    INDEX
    Explanations

    quantifiable units of time, particularly hours and minutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "hour" or "hours"

    np_acts-logits-general · gemini-2.0-flash

    elapsed time and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.69
     BoxDecoration
    -0.62
    elding
    -0.61
    chis
    -0.61
    IActionResult
    -0.59
    Controllo
    -0.59
    theless
    -0.59
     SPDX
    -0.59
     Kae
    -0.58
     Spisak
    -0.57
    POSITIVE LOGITS
     hours
    1.65
     Hours
    1.61
     HOURS
    1.55
    hours
    1.55
     HOUR
    1.43
    HOURS
    1.41
    Hours
    1.39
     hour
    1.38
    hour
    1.31
     Hour
    1.31
    Activations Density 0.070%

    No Known Activations