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. 25-GEMMASCOPE-RES-16K
    6. 1832
    Prev
    Next
    INDEX
    Explanations

    contextual references to installation or requirements in software-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     para
    -0.54
    Inggris
    -0.45
    Erreferentziak
    -0.44
     por
    -0.43
    Открыть
    -0.42
     Finalmente
    -0.40
     Rinehart
    -0.40
     кіль
    -0.40
    cri
    -0.40
    quoi
    -0.39
    POSITIVE LOGITS
     виправивши
    0.83
     تضيفلها
    0.77
     Як
    0.75
    Якщо
    0.73
     оригіналу
    0.71
    Як
    0.69
     الرياضيه
    0.65
    Від
    0.65
     Роз
    0.65
     Якщо
    0.63
    Activations Density 0.021%

    No Known Activations