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. 8684
    Prev
    Next
    INDEX
    Explanations

    technical jargon and programming-related 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
    )++;
    -0.25
    ⓧ
    -0.25
    tonode
    -0.20
    ViewImports
    -0.19
     חיצוני
    -0.18
    )}]{
    -0.18
    astéroïdes
    -0.18
    ficulty
    -0.18
    ignty
    -0.18
    vikle
    -0.18
    POSITIVE LOGITS
    <bos>
    0.91
    enumi
    0.38
    ρυ
    0.35
     estadounid
    0.35
    Clik
    0.35
     queſta
    0.33
    úb
    0.32
     ſei
    0.32
    нен
    0.32
     חיצוניים
    0.31
    Activations Density 36.173%

    No Known Activations