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. 12-GEMMASCOPE-RES-16K
    6. 4513
    Prev
    Next
    INDEX
    Explanations

    negations and their context in discussions about policies or legal implications

    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
     Ivanov
    -0.95
     Garibaldi
    -0.87
     Bennett
    -0.85
    Busch
    -0.81
     Alvin
    -0.78
     Garfield
    -0.77
     Arabs
    -0.77
     TTT
    -0.77
     Gerrard
    -0.77
     AssemblyCulture
    -0.76
    POSITIVE LOGITS
    DeleteBehavior
    0.91
     Mache
    0.75
     NOR
    0.74
    RuleContext
    0.70
     Meck
    0.70
    Mav
    0.69
     дописавши
    0.69
    Judi
    0.66
     〈
    0.65
    awtextra
    0.64
    Activations Density 0.715%

    No Known Activations