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. 15-GEMMASCOPE-RES-16K
    6. 12796
    Prev
    Next
    INDEX
    Explanations

    contextual relationships in collaborative environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sucre
    -0.52
    std
    -0.50
    copg
    -0.46
     Presto
    -0.46
     statis
    -0.45
     AEC
    -0.44
     skup
    -0.43
     fous
    -0.43
    MORE
    -0.43
     entière
    -0.43
    POSITIVE LOGITS
    OGND
    0.80
     ModelRenderer
    0.80
    TintMode
    0.79
    bootstrapcdn
    0.78
     other
    0.73
     the
    0.72
     fellow
    0.72
    ReusableCell
    0.71
     ويكيميديا
    0.69
     EconPapers
    0.67
    Activations Density 0.344%

    No Known Activations