© 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 EvalsExportsAPI 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. 80105
    Prev
    Next
    INDEX
    Explanations

    terms related to the shape and design of objects

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

    shape and size descriptors

    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
     avoient
    -0.56
     deberes
    -0.56
     juges
    -0.55
     pleaſure
    -0.54
     coucher
    -0.53
     plaît
    -0.52
     Leinwand
    -0.51
     prêtres
    -0.51
     Garantía
    -0.50
     TAMBIÉN
    -0.50
    POSITIVE LOGITS
    shaped
    0.61
    haped
    0.60
    iented
    0.54
    vorous
    0.54
    othed
    0.53
    quared
    0.52
    ainted
    0.52
    sized
    0.52
    lanted
    0.52
     Coloured
    0.51
    Activations Density 0.016%

    No Known Activations