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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 2475
    Prev
    Next
    INDEX
    Explanations

    references to groups or categories of items

    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
     Kleidung
    -0.71
     informaci
    -0.70
    dopodob
    -0.68
     barnet
    -0.65
    zieży
    -0.62
     Dul
    -0.62
     Zil
    -0.58
    addComponent
    -0.58
    ROIT
    -0.58
     gouttes
    -0.58
    POSITIVE LOGITS
     these
    1.31
    These
    1.29
     These
    1.22
     theses
    1.18
     THESE
    1.15
    these
    1.12
     Theses
    1.11
    这些
    1.00
    Эти
    1.00
     Theſe
    0.99
    Activations Density 0.130%

    No Known Activations