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. 9453
    Prev
    Next
    INDEX
    Explanations

    neural network activations that reflect mathematical or scientific data without context

    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
    tagHelperRunner
    -0.88
    AddTagHelper
    -0.69
    saraba
    -0.69
    enumii
    -0.66
    клопе
    -0.61
    findpost
    -0.60
    Література
    -0.60
    AddHtmlAttribute
    -0.58
    Източници
    -0.58
    ViewImports
    -0.56
    POSITIVE LOGITS
    libft
    0.50
    modelBuilder
    0.50
    <eos>
    0.46
     satisfied
    0.46
    grès
    0.45
    hoga
    0.44
    "]);
    
    0.44
     satisfecho
    0.44
     useCallback
    0.44
    Ис
    0.44
    Activations Density 0.036%

    No Known Activations