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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15683
    Prev
    Next
    INDEX
    Explanations

    terms related to racing and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Horse racing or related terms

    np_acts-logits-general · gemini-2.0-flash

    horse racing and modified wheels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.49
    WriteTagHelper
    -0.45
    tagHelperRunner
    -0.39
    Демографія
    -0.38
    IContainer
    -0.37
    dersfield
    -0.35
    pushFollow
    -0.34
    BeginContext
    -0.34
    implicitly
    -0.32
    országban
    -0.32
    POSITIVE LOGITS
     horses
    0.70
     trot
    0.69
     horsemen
    0.67
     racing
    0.64
     stallion
    0.61
     Breeders
    0.61
    horses
    0.61
     horseman
    0.61
     horse
    0.60
     harness
    0.57
    Activations Density 0.013%

    No Known Activations