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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15707
    Prev
    Next
    INDEX
    Explanations

    sports-related achievements or milestones

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

    Follows "the" and precedes a sports league

    np_acts-logits-general · gemini-2.0-flash

    sports leagues and conferences

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    帖最后由
    -0.70
    DBNull
    -0.60
     Picchu
    -0.60
     lenker
    -0.57
    ToolStripButton
    -0.53
     method
    -0.52
    TagHelper
    -0.51
    method
    -0.50
    тория
    -0.49
     ged
    -0.49
    POSITIVE LOGITS
     league
    1.23
     League
    1.00
    league
    0.95
     LEAGUE
    0.85
     leagues
    0.85
    League
    0.85
     conference
    0.71
     Leagues
    0.69
    httphttps
    0.69
     liga
    0.67
    Activations Density 0.149%

    No Known Activations