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. 23-GEMMASCOPE-RES-16K
    6. 6389
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and player conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.71
    WriteLiteral
    -0.68
    sizeCache
    -0.51
    principalColumn
    -0.49
    δή
    -0.49
    dura
    -0.48
    SpringRunner
    -0.48
    iteiten
    -0.47
    élien
    -0.47
    makeConstraints
    -0.47
    POSITIVE LOGITS
     home
    1.04
     road
    1.01
     away
    0.93
     games
    0.93
     matchup
    0.93
    home
    0.90
     hosting
    0.88
     game
    0.87
     matchups
    0.87
     rematch
    0.86
    Activations Density 0.225%

    No Known Activations