© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    themes of solitude and tranquility in nature

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

    being alone or quiet

    np_acts-logits-general · gemini-2.0-flash

    quiet, alone, or rural

    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
     prisonniers
    -0.42
    GIVEREF
    -0.38
    Geografía
    -0.37
    makeConstraints
    -0.36
     Administrativna
    -0.36
     Relaciones
    -0.36
     navideñas
    -0.35
     peix
    -0.35
    STRUCTIONS
    -0.34
    ErrUnexpectedEOF
    -0.34
    POSITIVE LOGITS
     quiet
    0.81
     quieter
    0.68
    quiet
    0.67
     secluded
    0.66
     Quiet
    0.65
     solitude
    0.63
    Quiet
    0.61
     privacy
    0.58
     silence
    0.55
    安静
    0.55
    Activations Density 0.129%

    No Known Activations