© 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. 20-GEMMASCOPE-RES-16K
    11. 11656
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their derivatives

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

    Chemical compounds or substituents

    np_acts-logits-general · gemini-2.0-flash

    pyrazines, quinolines, and naphthalene derivatives

    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
    featureID
    -0.64
    tagHelperRunner
    -0.62
    🏻‍♀️
    -0.61
     확인함
    -0.59
     Wicidata
    -0.58
    Koordinaten
    -0.58
    новниш
    -0.57
    脚注の使い方
    -0.56
     समीक्षाएं
    -0.53
    ‍♀️
    -0.53
    POSITIVE LOGITS
    abestanden
    0.73
    :+:
    0.69
     ring
    0.57
    ring
    0.56
    expandindo
    0.56
    々木
    0.55
     rings
    0.53
    Accessing
    0.52
    VideoCapture
    0.51
     saddle
    0.50
    Activations Density 0.465%

    No Known Activations