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. 21-GEMMASCOPE-RES-16K
    6. 12428
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports injuries and player status updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.49
     tief
    -0.44
    cheri
    -0.43
     Audiodateien
    -0.43
    Execute
    -0.43
    食い
    -0.42
    讲
    -0.41
    cate
    -0.41
    org
    -0.41
    RES
    -0.40
    POSITIVE LOGITS
     injury
    1.10
     Injury
    1.02
     injured
    1.01
    injury
    0.98
     Injured
    0.95
     injuries
    0.93
     blessé
    0.90
     INJ
    0.90
    Injury
    0.90
    Injuries
    0.89
    Activations Density 0.165%

    No Known Activations