© 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. 20-GEMMASCOPE-RES-16K
    11. 8495
    Prev
    Next
    INDEX
    Explanations

    terms related to various entities and classifications, specifically in contexts involving tag and policy frameworks

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

    Capitalized abbreviations

    np_acts-logits-general · gemini-2.0-flash

    Liushan

    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
    manteau
    -0.53
    gements
    -0.52
    autoconfigure
    -0.52
    ../../../
    -0.50
     Oldenburg
    -0.50
    ecto
    -0.49
    SequentialGroup
    -0.49
     Thessal
    -0.49
    StreetMap
    -0.48
    onalds
    -0.48
    POSITIVE LOGITS
    sili
    0.62
    fili
    0.60
    shi
    0.60
     Militia
    0.59
     ri
    0.58
     SIL
    0.57
    ielli
    0.57
    CIF
    0.57
    li
    0.56
     Titan
    0.56
    Activations Density 0.697%

    No Known Activations