© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105233
    Prev
    Next
    INDEX
    Explanations

    affirmations or confirmations in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Становништво
    -0.45
    éez
    -0.42
    textAppearance
    -0.41
     rainbow
    -0.41
    WindowConstants
    -0.40
     alexander
    -0.40
    MENAFN
    -0.40
    RenderAtEndOf
    -0.39
    direktor
    -0.38
     Tire
    -0.38
    POSITIVE LOGITS
     Chwiliwch
    0.69
    rungsseite
    0.45
    WriteTagHelper
    0.41
     Slightly
    0.40
    Slightly
    0.39
     presupposes
    0.39
    HandlerContext
    0.38
    :✨
    0.38
     ProtoMessage
    0.38
     cherchés
    0.37
    Activations Density 0.136%

    No Known Activations