© 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. 10263
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to performance metrics

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

    Numbers followed by a percentage or ratio

    np_acts-logits-general · gemini-2.0-flash

    percentages and rates

    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
    expandindo
    -0.79
     surla
    -0.78
     utafitiHapana
    -0.77
    ChildScrollView
    -0.75
     виправивши
    -0.74
     autorytatywna
    -0.74
    parsedMessage
    -0.73
     CanadaChoose
    -0.73
    InitVars
    -0.73
    ]")]
    -0.72
    POSITIVE LOGITS
     taux
    0.40
    率
    0.39
     yüzde
    0.36
     índices
    0.35
     rate
    0.34
    égard
    0.34
    %
    0.32
     obispo
    0.31
     tertinggi
    0.31
     própria
    0.30
    Activations Density 0.833%

    No Known Activations