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. 21-GEMMASCOPE-RES-16K
    6. 6906
    Prev
    Next
    INDEX
    Explanations

    references to icons or graphic representation elements

    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
    ValueStyle
    -0.69
    atimes
    -0.69
    addView
    -0.62
    moiselle
    -0.59
     Conducted
    -0.59
    PreInfinity
    -0.58
    Viited
    -0.57
    RepeatedField
    -0.57
    hoeddwyd
    -0.56
    BoxLayout
    -0.56
    POSITIVE LOGITS
     symbols
    0.76
     symbole
    0.71
     ICON
    0.67
     icon
    0.67
     icons
    0.67
     symbol
    0.66
     QtGui
    0.64
    Symbols
    0.63
    ography
    0.62
    symbols
    0.62
    Activations Density 0.089%

    No Known Activations