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. 20-GEMMASCOPE-RES-16K
    6. 12383
    Prev
    Next
    INDEX
    Explanations

    specific procedural details, particularly related to scientific or laboratory procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hours
    -0.72
     Hours
    -0.71
    Hour
    -0.70
     horas
    -0.65
     heures
    -0.64
     HOURS
    -0.64
     Hour
    -0.63
    Hours
    -0.63
    stunden
    -0.63
    yargs
    -0.62
    POSITIVE LOGITS
     seconds
    1.50
     minute
    1.13
     moments
    1.11
     moment
    1.08
    seconds
    1.08
     Seconds
    1.07
     SECON
    1.00
    moment
    1.00
     secondes
    0.98
     секун
    0.98
    Activations Density 0.488%

    No Known Activations