© 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. 5510
    Prev
    Next
    INDEX
    Explanations

    iconic representations or symbols often used in user interfaces

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

    Tokens preceding specific punctuation or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    fa plus or minus

    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
     récol
    -0.59
    cipar
    -0.54
     terminer
    -0.51
    дельник
    -0.49
     utafitiHapana
    -0.47
     Reisedaten
    -0.46
     Harbor
    -0.46
     하나
    -0.45
    RectangleBorder
    -0.45
     Improvement
    -0.45
    POSITIVE LOGITS
     Efq
    0.70
    出版年
    0.62
     <<<<<<<<<<<<<<
    0.60
     OFDb
    0.59
     gyhoeddwyd
    0.58
     Theſe
    0.57
     Faw
    0.57
     Reſ
    0.53
    igra
    0.53
     cref
    0.52
    Activations Density 0.040%

    No Known Activations