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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43288
    Prev
    Next
    INDEX
    Explanations

    references to capital punishment and its 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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    +#+#
    -0.56
    krat
    -0.52
    Stepper
    -0.50
     Muf
    -0.48
    Demografia
    -0.47
    Enders
    -0.46
    Subject
    -0.45
     Morav
    -0.45
    ШЕ
    -0.45
    hach
    -0.45
    POSITIVE LOGITS
    
    0.67
    AnimationsModule
    0.67
    Datuak
    0.64
    tagHelperRunner
    0.62
    nskap
    0.62
     مرئيه
    0.60
    BASELINE
    0.56
    HtmlAttribute
    0.55
    nitř
    0.54
    الدراسه
    0.54
    Activations Density 0.093%

    No Known Activations