© 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. 41-GEMMASCOPE-RES-16K
    6. 10795
    Prev
    Next
    INDEX
    Explanations

    corporate names and legal terminologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.73
    CloseOperation
    -0.59
    Билгалдахарш
    -0.56
     bad
    -0.55
     AssemblyCulture
    -0.50
    UrlResolution
    -0.49
    NegativeButton
    -0.47
    Autoritní
    -0.47
     بيها
    -0.45
     OMITBAD
    -0.44
    POSITIVE LOGITS
    .,,
    1.04
    .,.
    1.03
    ..,
    1.00
    .),
    0.88
    .,"
    0.88
    .],
    0.84
    .,
    0.78
    .;
    0.78
     .,
    0.77
    .},
    0.75
    Activations Density 0.433%

    No Known Activations