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. 20-GEMMASCOPE-RES-16K
    6. 2133
    Prev
    Next
    INDEX
    Explanations

    references to research and scientific studies

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

    followed by "is" or "team"

    np_acts-logits-general · gemini-2.0-flash

    research and its context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.93
    styleType
    -0.83
    arnings
    -0.71
    Izvori
    -0.70
     Վերցված
    -0.70
     ***!
    -0.68
    ButterKnife
    -0.65
    CloseOperation
    -0.63
     kasarigan
    -0.62
    cets
    -0.61
    POSITIVE LOGITS
     conducted
    0.56
     papers
    0.55
     gedaan
    0.53
    fulness
    0.51
     Papers
    0.49
     into
    0.49
     institutes
    0.48
     espar
    0.48
     findings
    0.48
    開発
    0.46
    Activations Density 0.061%

    No Known Activations