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. 16-GEMMASCOPE-RES-16K
    6. 12716
    Prev
    Next
    INDEX
    Explanations

    references to disciplinary actions in sports

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

    relating to altercations or calendar terms

    np_acts-logits-general · gemini-2.0-flash

    sending off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.70
    \{\\
    -0.64
     snippetHide
    -0.63
    GOTREF
    -0.63
    enumi
    -0.61
    <?
    -0.61
     Leaks
    -0.57
    ValueStyle
    -0.56
     radon
    -0.56
    Viitteet
    -0.56
    POSITIVE LOGITS
     violence
    0.86
     brawl
    0.82
     violent
    0.80
     braw
    0.78
     altercation
    0.76
     Violence
    0.74
    Violence
    0.73
    violence
    0.72
     aggression
    0.69
     fracas
    0.67
    Activations Density 0.394%

    No Known Activations