© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3948
    Prev
    Next
    INDEX
    Explanations

    keywords related to engineering, training, diagnosis, and health outcomes

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

    followed by "and"

    np_acts-logits-general · gemini-2.0-flash

    and, but, or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     EconPapers
    -0.68
     resourceCulture
    -0.60
     verſch
    -0.57
     invokingState
    -0.57
    contentLoaded
    -0.57
     חיצוניים
    -0.57
     geſch
    -0.55
    цездатний
    -0.55
    KommentareTeilen
    -0.54
     disambiguazione
    -0.54
    POSITIVE LOGITS
     and
    1.06
     &
    0.55
    性和
    0.52
    และ
    0.49
     və
    0.45
    力和
    0.45
     एवं
    0.45
     및
    0.43
     आणि
    0.41
    子和
    0.40
    Activations Density 1.116%

    No Known Activations