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. 12910
    Prev
    Next
    INDEX
    Explanations

    numeric values related to time periods or lengths of employment

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

    Numbers followed by time units

    np_acts-logits-general · gemini-2.0-flash

    time durations: weeks, months, years

    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
     متعلقه
    -0.55
     HasFactory
    -0.52
    rungsseite
    -0.51
    <()>
    -0.50
    ->_
    -0.49
    юза
    -0.49
    nestjs
    -0.48
     defaultstate
    -0.47
    ())->
    -0.47
    atissimo
    -0.47
    POSITIVE LOGITS
     weeks
    1.35
     months
    1.25
    weeks
    1.11
     years
    1.11
    months
    1.05
     days
    1.03
     WEEKS
    1.02
     Months
    1.02
     Weeks
    1.01
     MONTHS
    0.98
    Activations Density 0.435%

    No Known Activations