© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 15259
    Prev
    Next
    INDEX
    Explanations

    statistics related to player performance in sports

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

    Statistics related to sports

    np_acts-logits-general · gemini-2.0-flash

    sports statistics performance metrics

    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
    posób
    -0.47
    ínű
    -0.47
     المعيارى
    -0.46
    UnusedPrivate
    -0.46
     محفوظة
    -0.44
    pirable
    -0.42
    RestTemplate
    -0.41
    bijt
    -0.41
    sweetalert
    -0.41
    غراف
    -0.40
    POSITIVE LOGITS
     career
    0.71
     average
    0.70
    TagMode
    0.70
    verages
    0.67
     league
    0.65
     ERA
    0.63
     averages
    0.62
     moyenne
    0.62
    __':
    
    0.61
     Adjusted
    0.60
    Activations Density 0.221%

    No Known Activations