© 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. 3482
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terms, particularly related to chemical compounds and biological research

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

    ending in "on", "ion", "tron", or "azon"

    np_acts-logits-general · gemini-2.0-flash

    words ending in 'on' or 'ion'

    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
    הערות
    -0.67
    /***/
    -0.66
    TagHelper
    -0.63
    conio
    -0.57
    SizeMode
    -0.57
    LayoutConstraint
    -0.57
    guez
    -0.56
     latter
    -0.56
    ibatis
    -0.55
    schrift
    -0.55
    POSITIVE LOGITS
    nnnn
    0.96
    nnn
    0.82
    ized
    0.81
    ization
    0.77
     Rondo
    0.72
    cino
    0.72
    naires
    0.71
    ian
    0.71
    ostante
    0.71
    ality
    0.71
    Activations Density 0.527%

    No Known Activations