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. 5-GEMMASCOPE-RES-16K
    6. 2866
    Prev
    Next
    INDEX
    Explanations

    structured programming elements like type definitions and function signatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hauptartikel
    -0.55
     sorti
    -0.53
    кож
    -0.52
     dessinée
    -0.50
    presso
    -0.48
    ècie
    -0.48
    unhofer
    -0.46
     okuyayım
    -0.46
     Durée
    -0.46
    Newswire
    -0.46
    POSITIVE LOGITS
     Efq
    0.69
     ویکی‌پدیا
    0.67
     Holman
    0.66
    HasIndex
    0.64
    contentLoaded
    0.63
    :^(
    0.60
     officio
    0.60
     Houſe
    0.58
    ("/:
    0.58
    água
    0.57
    Activations Density 0.078%

    No Known Activations