© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5421
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and transitions between ideas or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    beginning of new sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.63
    protoc
    -0.59
    håll
    -0.57
    一応
    -0.55
     désolés
    -0.54
    unque
    -0.53
     irgende
    -0.52
    usda
    -0.51
    覚悟
    -0.51
    cuno
    -0.51
    POSITIVE LOGITS
     by
    1.23
     By
    1.15
     dadurch
    1.12
    By
    1.12
     using
    1.11
    Using
    1.05
     Using
    1.04
     grâce
    1.02
     dzięki
    1.02
     באמצעות
    1.00
    Activations Density 0.333%

    No Known Activations