© 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. 13185
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to safety razors and their maintenance

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

    frequency or repetition

    np_acts-logits-general · gemini-2.0-flash

    time, replacement, refills, durability

    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
     Deckel
    -0.35
     przysz
    -0.35
     navideñas
    -0.33
     communis
    -0.33
    Contr
    -0.32
     FT
    -0.32
     {},
    -0.32
    (")");
    -0.32
    gó
    -0.31
    Opportun
    -0.31
    POSITIVE LOGITS
     nahilalakip
    0.88
     &___
    0.59
     ویکی‌پدیا
    0.59
    RotationOrder
    0.51
     OnInit
    0.50
    Билгалдахарш
    0.48
    oa̍t
    0.47
    parsedMessage
    0.47
    ésult
    0.46
    structors
    0.46
    Activations Density 0.259%

    No Known Activations