© 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. 37-GEMMASCOPE-RES-16K
    6. 713
    Prev
    Next
    INDEX
    Explanations

    requests for help or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSError
    -0.38
    kegaard
    -0.35
    naeus
    -0.32
    MLLoader
    -0.30
    awaiter
    -0.30
    dicht
    -0.29
     beden
    -0.28
    execSQL
    -0.28
     صلاح
    -0.28
    ungszeit
    -0.28
    POSITIVE LOGITS
     thank
    3.70
     thanks
    3.63
     Thank
    3.25
     Thanks
    3.20
    thanks
    3.13
    thank
    3.09
     THANKS
    3.02
    Thanks
    3.00
    Thank
    2.98
     thanked
    2.91
    Activations Density 0.717%

    No Known Activations