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

    Neuronpedia

    Jacobian LensNEW
    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. 16-GEMMASCOPE-RES-16K
    11. 13831
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation marks used in mathematical or programming contexts

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

    Non-English text and numbers

    np_acts-logits-general · gemini-2.0-flash

    6 weeks, not optimistic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osgi
    -0.54
    <eos>
    -0.50
     東京都
    -0.48
    seud
    -0.47
    uParam
    -0.47
    ::{
    -0.46
     model
    -0.45
    ohar
    -0.45
    ↵↵
    -0.45
     Speedway
    -0.45
    POSITIVE LOGITS
    دانشنامهٔ
    1.05
    elemField
    0.95
     مرئيه
    0.88
     Roskov
    0.86
    bootstrapcdn
    0.85
    expandindo
    0.85
    NameInMap
    0.83
    +#+#
    0.82
    AnimationsModule
    0.78
    ArgsConstructor
    0.76
    Activations Density 0.444%

    No Known Activations