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. 16-GEMMASCOPE-RES-16K
    6. 1550
    Prev
    Next
    INDEX
    Explanations

    URLs and references for academic papers and articles

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

    arXiv references with bracketed numbers

    np_acts-logits-general · gemini-2.0-flash

    arXiv identifiers and links

    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
     tartalomajánló
    -0.70
    يميديا
    -0.67
     officiers
    -0.62
     незавершена
    -0.60
     gardes
    -0.59
    routeProvider
    -0.58
     sauvage
    -0.57
    NameInMap
    -0.57
     fidélité
    -0.56
    subpackage
    -0.56
    POSITIVE LOGITS
    arXiv
    1.05
     arXiv
    0.59
     arxiv
    0.56
    herjee
    0.52
     referenties
    0.51
    APORE
    0.50
     papers
    0.50
    FileList
    0.48
    abestanden
    0.46
     indisponible
    0.45
    Activations Density 0.016%

    No Known Activations