© 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. 13-GEMMASCOPE-RES-16K
    11. 9511
    Prev
    Next
    INDEX
    Explanations

    complex ideas and the need for careful interpretation in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @@@@@
    -0.38
     á
    -0.36
    OrUpdate
    -0.35
    <()>
    -0.35
     dra
    -0.34
    <_>
    -0.34
     ai
    -0.34
     div
    -0.34
    bital
    -0.34
     cos
    -0.34
    POSITIVE LOGITS
     Majefty
    0.75
     myſelf
    0.71
     Anſ
    0.69
     houſe
    0.65
     Reſ
    0.63
     pleaſure
    0.62
     abstrato
    0.61
     Perſ
    0.60
     meille
    0.60
     Houſe
    0.60
    Activations Density 0.686%

    No Known Activations