© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 34470
    Prev
    Next
    INDEX
    Explanations

    characteristics of items, specifically focusing on attributes like size, condition, and material

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

    clothing descriptions

    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
    onViewCreated
    -0.33
    newtheorem
    -0.33
     depor
    -0.33
    دانشنامهٔ
    -0.33
     BoxDecoration
    -0.32
    ocidad
    -0.31
     encom
    -0.30
     distribution
    -0.30
    +#+
    -0.29
     proposals
    -0.29
    POSITIVE LOGITS
    sizeCache
    0.50
     SafeMath
    0.48
    teva
    0.47
    SpringRunner
    0.47
    AntiForgeryToken
    0.46
    fatt
    0.45
    ashion
    0.45
    SourceChecksum
    0.45
    label
    0.45
    mbg
    0.45
    Activations Density 0.003%

    No Known Activations