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. 20-GEMMASCOPE-RES-16K
    6. 2832
    Prev
    Next
    INDEX
    Explanations

    quantum-related concepts or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.97
     صوتيه
    -0.89
    Искәрмәләр
    -0.86
     EconPapers
    -0.85
    LookAnd
    -0.85
    Билгалдахарш
    -0.84
     الرياضيه
    -0.84
    WebElementEntity
    -0.83
    ThroughAttribute
    -0.78
    ConstraintMaker
    -0.78
    POSITIVE LOGITS
    me
    0.53
     re
    0.52
    Re
    0.52
    RE
    0.52
    <eos>
    0.47
     ins
    0.47
     Процитовано
    0.45
    re
    0.45
     Re
    0.43
    der
    0.43
    Activations Density 0.169%

    No Known Activations