© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9001
    Prev
    Next
    INDEX
    Explanations

    names of authors and their respective contributions

    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
     Gries
    -0.44
     Kowalski
    -0.44
     Leal
    -0.43
     Dominguez
    -0.42
     “
    -0.40
     Thacker
    -0.40
     deverá
    -0.39
     Domínguez
    -0.39
     ‘
    -0.38
     katholischen
    -0.38
    POSITIVE LOGITS
     informée
    0.66
     autorytatywna
    0.65
     Administrativna
    0.61
     témoig
    0.54
    ſelben
    0.52
     incrí
    0.52
     disambiguazione
    0.52
     Italijanski
    0.50
     increí
    0.50
     gynhyrchwyd
    0.50
    Activations Density 0.242%

    No Known Activations