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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 13909
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of work and work-life balance

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

    "work" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    work unit and related outputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.80
    findpost
    -0.76
    RenderAtEndOf
    -0.65
    ագրություններ
    -0.65
    CodeAttribute
    -0.62
    AppMethodBeat
    -0.59
    AsUp
    -0.58
    তথ্যসূত্র
    -0.57
    XmlAccessType
    -0.56
    setVerticalGroup
    -0.55
    POSITIVE LOGITS
    force
    0.72
    place
    0.70
    PLACE
    0.69
     force
    0.67
     place
    0.63
     Force
    0.63
    Force
    0.62
    orce
    0.62
    places
    0.61
    FORCE
    0.60
    Activations Density 0.121%

    No Known Activations