© 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. 20-GEMMASCOPE-RES-16K
    11. 15368
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their relationships in sentences

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

    Follows commas or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    examples, parentheticals, or asides

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     which
    -0.67
    béco
    -0.61
    hich
    -0.61
    which
    -0.61
     jossa
    -0.58
    ыгана
    -0.57
    יוחד
    -0.57
    出版年
    -0.56
     MenuView
    -0.56
    optarg
    -0.55
    POSITIVE LOGITS
     appunto
    0.82
     brevemente
    0.61
    Personendaten
    0.59
    TestingModule
    0.58
     ironically
    0.57
    AnimationsModule
    0.55
     temporaire
    0.54
    SPOILER
    0.54
     albeit
    0.54
    帖最后由
    0.54
    Activations Density 0.313%

    No Known Activations