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. 24-GEMMASCOPE-RES-16K
    6. 13729
    Prev
    Next
    INDEX
    Explanations

    references to events or achievements in a sports context, particularly those involving game statistics or player performances

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

    "...season" or "...year"

    np_acts-logits-general · gemini-2.0-flash

    this season or last season

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [*]
    -0.61
    netbeans
    -0.56
     financeira
    -0.55
    XtraGrid
    -0.55
    richTextPanel
    -0.51
    ngiliz
    -0.50
    帖最后由
    -0.50
    jabat
    -0.49
    Становништво
    -0.49
     geko
    -0.48
    POSITIVE LOGITS
     season
    2.38
    season
    1.82
     Season
    1.61
     SEASON
    1.58
     seasons
    1.57
    Season
    1.55
     saison
    1.45
    SEASON
    1.39
     temporada
    1.35
     seizoen
    1.28
    Activations Density 0.150%

    No Known Activations