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. 24-GEMMASCOPE-RES-16K
    6. 16357
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports teams and their performance

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

    Sports-related articles and discussions

    np_acts-logits-general · gemini-2.0-flash

    football player status

    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
     Lyra
    -0.56
     Judith
    -0.51
    behaviour
    -0.49
    cyjna
    -0.49
     Whilst
    -0.49
     behaviour
    -0.48
     standardised
    -0.47
     strumenti
    -0.47
    organised
    -0.47
    neighbours
    -0.46
    POSITIVE LOGITS
     offseason
    1.04
     coaches
    0.97
     preseason
    0.95
     Belich
    0.91
     NFL
    0.88
     players
    0.85
     Coaches
    0.85
     postseason
    0.85
     coaching
    0.85
     player
    0.85
    Activations Density 0.554%

    No Known Activations