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. 3-GEMMASCOPE-RES-16K
    6. 11230
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to "den," "denominations," and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Katrin
    -0.66
     Zwie
    -0.63
     Blackwell
    -0.56
    Pvt
    -0.55
    toPromise
    -0.55
     Weinberg
    -0.54
     asset
    -0.54
     corri
    -0.54
    addObject
    -0.53
    inhardt
    -0.53
    POSITIVE LOGITS
    Den
    3.33
     Den
    3.28
     den
    3.21
     DEN
    3.01
    den
    2.83
    DEN
    2.59
    deno
    1.72
     Denial
    1.61
     Dens
    1.60
     Denison
    1.60
    Activations Density 0.100%

    No Known Activations