© 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. 10242
    Prev
    Next
    INDEX
    Explanations

    references to community interaction and support related to health and social issues

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

    Follows certain nouns or verbs, often capitalized

    np_acts-logits-general · gemini-2.0-flash

    federal rules or sections

    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
     trenes
    -0.45
    hythm
    -0.40
     progrès
    -0.38
     yorum
    -0.36
     considérons
    -0.35
     sahiptir
    -0.35
     çe
    -0.35
     treno
    -0.34
     Gründe
    -0.33
    เฉ
    -0.33
    POSITIVE LOGITS
     okuyayım
    0.61
    OGND
    0.53
    Diweddarwch
    0.52
    UIControlState
    0.48
    FailureListener
    0.47
    statin
    0.47
    رشف
    0.47
    writeField
    0.47
     Paglinawan
    0.47
    inghouse
    0.46
    Activations Density 0.662%

    No Known Activations