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. 21-GEMMASCOPE-RES-16K
    6. 14324
    Prev
    Next
    INDEX
    Explanations

    user interface components and their configurations in a programming context

    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
    <eos>
    -0.62
     
    -0.61
    ?
    -0.56
     e
    -0.54
     all
    -0.51
    =
    -0.50
    HideFlags
    -0.49
     a
    -0.48
     (
    -0.48
    ThemeOverlay
    -0.48
    POSITIVE LOGITS
     myſelf
    0.88
     ་་
    0.82
     ―――――
    0.77
     itſelf
    0.76
     ſhe
    0.75
     Efq
    0.74
     Theſe
    0.72
    esgue
    0.71
     SOB
    0.70
     AGB
    0.70
    Activations Density 0.009%

    No Known Activations