© 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. 35-GEMMASCOPE-RES-16K
    11. 12322
    Prev
    Next
    INDEX
    Explanations

    references to product launches and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.34
     tác
    -0.32
    orsese
    -0.32
    guisement
    -0.32
    tifikat
    -0.30
    ствии
    -0.30
    Reproduction
    -0.29
    逞
    -0.29
    czer
    -0.29
    Miejs
    -0.29
    POSITIVE LOGITS
     launch
    3.25
     launched
    2.89
     launching
    2.84
     launches
    2.75
    launch
    2.75
     Launch
    2.69
    Launch
    2.53
     Launching
    2.52
    launched
    2.50
    Launching
    2.47
    Activations Density 0.447%

    No Known Activations