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. 16-GEMMASCOPE-RES-16K
    6. 12263
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text after periods, numbers or colons

    np_acts-logits-general · gemini-2.0-flash

    following a sentence's beginning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.82
    PageContext
    -0.73
     AssemblyProduct
    -0.68
    BeginContext
    -0.68
     ſtate
    -0.66
     Ngb
    -0.63
    SourceChecksum
    -0.60
     Chriſt
    -0.59
    tamment
    -0.59
    WebServlet
    -0.59
    POSITIVE LOGITS
    DeleteBehavior
    0.55
    albeit
    0.51
    rather
    0.49
    DataAnnotations
    0.49
    ',{
    0.49
    ::_('
    0.48
    Whilst
    0.48
    )))));
    0.48
    UGE
    0.47
    warzys
    0.47
    Activations Density 0.232%

    No Known Activations