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. 2945
    Prev
    Next
    INDEX
    Explanations

    references to figures and equations in scientific literature

    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
    FormTagHelper
    -0.75
    ConstraintMaker
    -0.68
     snippetHide
    -0.67
    GEBURTSDATUM
    -0.63
    rrggbb
    -0.61
    findpost
    -0.60
     resourceCulture
    -0.59
    InjectAttribute
    -0.59
    ValueStyle
    -0.55
    Jegyzetek
    -0.55
    POSITIVE LOGITS
    )_/¯
    0.60
    Ран
    0.53
    ondissement
    0.48
     méthode
    0.47
     tradizione
    0.46
    template
    0.46
     tradición
    0.46
     gebru
    0.46
     blanch
    0.46
    :+:
    0.46
    Activations Density 1.093%

    No Known Activations