© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11412
    Prev
    Next
    INDEX
    Explanations

    statistical significance and relevant p-values in research contexts

    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
    SourceChecksum
    -0.65
    ScopeManager
    -0.54
     MainAxisSize
    -0.48
    󠁿
    -0.47
    pipe
    -0.45
     disambiguazione
    -0.43
    TagHelpers
    -0.43
    patch
    -0.42
     كومونز
    -0.42
    patio
    -0.41
    POSITIVE LOGITS
     P
    2.42
     p
    2.41
    P
    1.77
    p
    1.66
     getP
    1.60
    setP
    1.47
    getP
    1.34
     پ
    1.34
     п
    1.15
     प
    1.13
    Activations Density 1.899%

    No Known Activations