© 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. 11654
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of "saccharomyces" and "vacuum" in a scientific context

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

    Followed by "ac," "rific," or "illus"

    np_acts-logits-general · gemini-2.0-flash

    sac, vac, bac beginnings

    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
    Hauptartikel
    -0.64
    +:+
    -0.63
    ChildScrollView
    -0.59
    damento
    -0.58
    씬
    -0.58
    RenderAtEndOf
    -0.57
    tki
    -0.56
    hassee
    -0.56
     Werth
    -0.56
    SharedCtor
    -0.54
    POSITIVE LOGITS
    sac
    0.55
    HS
    0.53
    sin
    0.53
     nac
    0.51
    SAC
    0.50
    son
    0.50
    support
    0.49
    cama
    0.49
    pac
    0.47
    ac
    0.47
    Activations Density 0.184%

    No Known Activations