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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1786
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to programming or software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    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
    NewGuid
    -0.48
    devServer
    -0.45
    ậy
    -0.43
    кипе
    -0.42
    var
    -0.42
    erover
    -0.41
    photobucket
    -0.41
    endpush
    -0.41
    mixin
    -0.41
    ValueGeneration
    -0.40
    POSITIVE LOGITS
     disambiguazione
    0.89
     تضيفلها
    0.84
    rungsseite
    0.71
     ddelweddau
    0.70
     تانيه
    0.70
    verwijspagina
    0.69
     Monfieur
    0.68
     ſind
    0.67
    homonymie
    0.66
    Begriffsklä
    0.66
    Activations Density 0.115%

    No Known Activations