© 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. 6263
    Prev
    Next
    INDEX
    Explanations

    text related to inscriptions and markings on various objects

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

    inscriptions or markings

    np_acts-logits-general · gemini-2.0-flash

    textual or decorative markings

    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
     malades
    -0.45
     NACIONAL
    -0.40
     reposer
    -0.39
    Cordialement
    -0.39
    Conclusie
    -0.38
    igreja
    -0.38
     circonstances
    -0.38
     principes
    -0.37
    atasi
    -0.36
     ejecutivo
    -0.36
    POSITIVE LOGITS
     markings
    0.58
     gynhyrchwyd
    0.57
     صوتيه
    0.56
    ukone
    0.56
    GEBURTSDATUM
    0.54
     فريبيس
    0.53
    Билгалдахарш
    0.50
    tellations
    0.49
    marking
    0.49
    AddHtmlAttribute
    0.48
    Activations Density 0.529%

    No Known Activations