© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 37489
    Prev
    Next
    INDEX
    Explanations

    identifiers and codes, often used in scientific or technical contexts

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

    technical identifiers and citations

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     razonable
    -0.47
     adecuadas
    -0.46
     few
    -0.45
     bestemt
    -0.44
     respectivas
    -0.44
     apropiado
    -0.44
     Ahnung
    -0.42
     partly
    -0.42
     sufficient
    -0.42
     sometimes
    -0.42
    POSITIVE LOGITS
     nakalista
    0.83
     nonUne
    0.58
    Manbalar
    0.56
    Kaynakça
    0.54
    Parcelize
    0.50
    әрмәләр
    0.47
     ویکی‌پدی
    0.47
    Yah
    0.46
    NEM
    0.46
     UserModel
    0.45
    Activations Density 0.216%

    No Known Activations