© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 7129
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming interfaces and symbol definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.74
    LookAnd
    -0.73
    IsContent
    -0.70
    OCCURRED
    -0.60
    NameInMap
    -0.60
    CodeAttribute
    -0.59
    ThemeOverlay
    -0.58
    AntiForgeryToken
    -0.57
    twimg
    -0.56
    Portail
    -0.56
    POSITIVE LOGITS
     تضيفلها
    0.63
    ptonshire
    0.62
    hidupan
    0.61
    setVerticalGroup
    0.61
    odeon
    0.58
    Geograf
    0.57
     elettron
    0.56
    moiselle
    0.55
     Picchu
    0.53
     vides
    0.53
    Activations Density 0.770%

    No Known Activations