© 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
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 8386
    Prev
    Next
    INDEX
    Explanations

    elements and attributes commonly found in XML or structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hoeddwyd
    -0.59
    queryInterface
    -0.56
    postsleuth
    -0.50
    sizeCache
    -0.48
     ModelExpression
    -0.47
    parsedMessage
    -0.46
     mío
    -0.43
     lluvias
    -0.42
    UrlResolution
    -0.42
    mappedBy
    -0.42
    POSITIVE LOGITS
    protoimpl
    0.52
     Alternate
    0.48
     qualifier
    0.48
     متعلقه
    0.46
     observation
    0.44
     qualifiers
    0.44
    etary
    0.43
     scho
    0.43
     associated
    0.43
    urn
    0.41
    Activations Density 1.516%

    No Known Activations