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. 6036
    Prev
    Next
    INDEX
    Explanations

    references to academic publications, including titles, authors, publication years, and locations

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

    Numbers within parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    citation numbers or identifiers

    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
     nahilalakip
    -0.55
    ,‎
    -0.52
    året
    -0.52
     is
    -0.47
     most
    -0.47
    PositiveButton
    -0.47
    glDelete
    -0.46
    addEventListener
    -0.46
    </thead>
    -0.45
    arre
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.99
    AddTagHelper
    0.74
    adaptiveStyles
    0.70
     surla
    0.65
    المشاركات
    0.63
    endpush
    0.61
     holotype
    0.61
    tvguidetime
    0.60
    werve
    0.58
    nodoc
    0.58
    Activations Density 0.217%

    No Known Activations