Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 523
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the concept of "second" and its various contextual uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.72
     Theſe
    -0.67
    %)$
    -0.63
     Winaray
    -0.63
     acolo
    -0.60
     whofe
    -0.60
     initComponents
    -0.59
    ="#"><
    -0.57
    either
    -0.57
     kasarigan
    -0.57
    POSITIVE LOGITS
    arily
    1.08
    aries
    0.91
     والث
    0.69
     largest
    0.68
     half
    0.66
     baseman
    0.66
    ment
    0.66
    hand
    0.65
    largest
    0.64
     tier
    0.63
    Activations Density 0.143%

    No Known Activations