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. 5-GEMMASCOPE-RES-16K
    6. 4521
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     اطلع
    -0.54
     unterschiedlich
    -0.51
     tenuto
    -0.48
     Attic
    -0.48
     Lengkap
    -0.47
     stringBy
    -0.47
     reconoci
    -0.47
     cistern
    -0.46
     livré
    -0.46
     perſon
    -0.46
    POSITIVE LOGITS
     ProtoMessage
    0.88
    ScopeManager
    0.80
    WithIOException
    0.78
     fieldNum
    0.73
    RenderAtEndOf
    0.71
    endpush
    0.71
    enumii
    0.70
     समीक्षाओं
    0.69
    CppMethod
    0.68
    enumi
    0.67
    Activations Density 0.253%

    No Known Activations