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. 0-GEMMASCOPE-RES-16K
    6. 6380
    Prev
    Next
    INDEX
    Explanations

    instances of the term "nil" and its relevance in the context of errors or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /
    -0.56
     wall
    -0.51
     non
    -0.50
     community
    -0.49
     r
    -0.49
     D
    -0.48
     we
    -0.47
     F
    -0.46
    liminary
    -0.46
     M
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.96
    WithIOException
    0.95
     initComponents
    0.90
     AssemblyCompany
    0.86
    IsMutable
    0.86
     مرئيه
    0.85
     <",
    0.85
     surla
    0.84
     chi̍t
    0.84
     nakalista
    0.82
    Activations Density 0.119%

    No Known Activations