Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7933
    Prev
    Next
    INDEX
    Explanations

    references to significant awards or accolades related to women

    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
     مرئيه
    -0.64
     ProtoMessage
    -0.59
     resten
    -0.58
    idée
    -0.58
     EconPapers
    -0.57
     biais
    -0.55
     ranks
    -0.55
     ritmo
    -0.54
     possibilité
    -0.53
     uso
    -0.52
    POSITIVE LOGITS
    zeitige
    0.71
     beholder
    0.65
    zeiti
    0.62
    abestanden
    0.61
    Демографія
    0.61
     century
    0.59
     preceding
    0.59
     fittest
    0.59
     respective
    0.58
    ittarius
    0.57
    Activations Density 0.569%

    No Known Activations