© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7228
    Prev
    Next
    INDEX
    Explanations

    references to soccer-related activities and careers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Race
    -0.57
    Race
    -0.54
    RACE
    -0.49
     RACE
    -0.48
     batted
    -0.46
    Practices
    -0.44
     ujednoznacz
    -0.44
     Swim
    -0.43
    Play
    -0.43
    🎾
    -0.43
    POSITIVE LOGITS
     professional
    0.90
     profesional
    0.77
    professional
    0.75
     professionally
    0.71
     elite
    0.71
     amateur
    0.64
     profesionales
    0.63
     professionnel
    0.63
     profes
    0.62
     collegiate
    0.61
    Activations Density 0.319%

    No Known Activations