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. 22-GEMMASCOPE-RES-16K
    6. 10268
    Prev
    Next
    INDEX
    Explanations

    phrases related to player injuries and their implications

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

    player injuries

    np_acts-logits-general · gemini-2.0-flash

    injured or out of play

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.54
    食い
    -0.45
     annehmen
    -0.43
    closePath
    -0.42
    Execute
    -0.42
    லை
    -0.42
     mortes
    -0.41
    UAWEI
    -0.41
     Evers
    -0.41
    وال
    -0.40
    POSITIVE LOGITS
     injury
    1.07
     injured
    1.01
     Injury
    0.97
    injury
    0.96
     missed
    0.92
     Injured
    0.92
     INJ
    0.90
    Injury
    0.89
     sidelined
    0.89
     miss
    0.86
    Activations Density 0.190%

    No Known Activations