© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12727
    Prev
    Next
    INDEX
    Explanations

    numerical values and their associated metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    čios
    -0.48
    mær
    -0.39
     cuenca
    -0.38
     Aufnahme
    -0.38
    6
    -0.37
    isielt
    -0.37
     almendras
    -0.36
     rallado
    -0.35
     juos
    -0.35
     mourut
    -0.35
    POSITIVE LOGITS
    9
    0.65
     nine
    0.65
     ninety
    0.63
     estekak
    0.62
     Chwiliwch
    0.60
     يتيمه
    0.59
    abetes
    0.58
    ⁹
    0.57
     snippetHide
    0.56
     ninth
    0.56
    Activations Density 0.651%

    No Known Activations