© 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. 15-GEMMASCOPE-RES-16K
    11. 1260
    Prev
    Next
    INDEX
    Explanations

    activities related to outdoor exploration and culinary experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.52
    tangentMode
    -0.42
    VYMaps
    -0.40
     setuptools
    -0.36
    Parms
    -0.35
    roffene
    -0.35
    олові
    -0.34
    IInterface
    -0.34
    setVerticalGroup
    -0.34
     circonstances
    -0.33
    POSITIVE LOGITS
    TagMode
    0.57
    Télécharger
    0.48
    rrggbb
    0.48
    GOTREF
    0.46
     صفحۀ
    0.46
     downloaded
    0.45
     informée
    0.44
     downloading
    0.44
     disambiguazione
    0.44
    downloaded
    0.43
    Activations Density 0.229%

    No Known Activations