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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 12676
    Prev
    Next
    INDEX
    Explanations

    terms related to horse breeding and veterinary practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SPAN
    -0.72
     Prakash
    -0.65
    rinks
    -0.65
    UTERS
    -0.62
    Dowell
    -0.61
     Архи
    -0.60
    adaptiveStyles
    -0.59
    bilis
    -0.59
     Sagar
    -0.59
     Moines
    -0.59
    POSITIVE LOGITS
     horses
    1.39
     Horses
    1.35
     horse
    1.34
    Horses
    1.28
    horses
    1.27
     Horse
    1.26
     equine
    1.26
    horse
    1.23
     HORSE
    1.21
    Horse
    1.16
    Activations Density 0.596%

    No Known Activations