Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 1459
    Prev
    Next
    INDEX
    Explanations

    instances of grappling and submission techniques in combat sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.61
    forName
    -0.57
     parallelism
    -0.57
     Morte
    -0.57
    Hentet
    -0.56
     Freeway
    -0.55
    énieur
    -0.54
     Expressway
    -0.53
    íncia
    -0.53
     vibrate
    -0.53
    POSITIVE LOGITS
     UFC
    0.97
     MMA
    0.91
    MMA
    0.79
     boxing
    0.77
    quiao
    0.77
     ufc
    0.77
    UFC
    0.77
    BufferException
    0.76
    🥊
    0.75
     fighters
    0.72
    Activations Density 0.205%

    No Known Activations