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. 13-GEMMASCOPE-RES-16K
    6. 10318
    Prev
    Next
    INDEX
    Explanations

    no specific significant activations, indicating it does not detect any particular feature or information in the given document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.69
     “
    -0.63
     that
    -0.61
     new
    -0.60
     and
    -0.60
     this
    -0.58
     make
    -0.57
     big
    -0.56
     full
    -0.56
     tõ
    -0.55
    POSITIVE LOGITS
    AnimationsModule
    0.75
    EndProject
    0.67
     Himo
    0.66
    </caption>
    0.65
    piram
    0.65
    InstrumentedTest
    0.64
     disambiguazione
    0.64
    IsMutable
    0.63
    SourceChecksum
    0.62
     Chwiliwch
    0.62
    Activations Density 0.170%

    No Known Activations