© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12597
    Prev
    Next
    INDEX
    Explanations

    references to online communication and transactions

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

    Follows end-of-turn tokens

    np_acts-logits-general · gemini-2.0-flash

    examples following "such" or "kind"

    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
    webElementXpaths
    -0.49
     Numerade
    -0.46
     nawr
    -0.44
    HasColumnName
    -0.41
    vible
    -0.39
     instructors
    -0.38
    請繼續往下閱讀
    -0.38
    urably
    -0.38
    Xna
    -0.37
    XmlAccessorType
    -0.37
    POSITIVE LOGITS
     للاسماء
    0.52
    setVerticalGroup
    0.47
    DoubleQuotes
    0.44
    MessageOf
    0.44
     certificat
    0.42
    therlands
    0.41
    enumii
    0.41
    contentLoaded
    0.40
    certificate
    0.40
     CanadaChoose
    0.40
    Activations Density 0.261%

    No Known Activations