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. 12289
    Prev
    Next
    INDEX
    Explanations

    references to sports apparel and athlete performance

    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
    ########.
    -0.67
     consultato
    -0.63
     professionali
    -0.59
     protoimpl
    -0.57
     alha
    -0.57
    ักษ
    -0.56
     Efq
    -0.56
     Brice
    -0.55
     Dolls
    -0.55
     dolls
    -0.52
    POSITIVE LOGITS
     runners
    1.01
     Runners
    1.00
    runners
    0.95
     runner
    0.93
    runner
    0.85
     Runner
    0.84
     jogging
    0.84
     tracksuit
    0.81
     Running
    0.81
     jogger
    0.78
    Activations Density 0.465%

    No Known Activations