© 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. 2-GEMMASCOPE-RES-16K
    11. 14972
    Prev
    Next
    INDEX
    Explanations

    abbreviations and terms related to technical specifications or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dietz
    -0.47
     Burch
    -0.42
    ########.
    -0.42
     Darlene
    -0.40
     Dar
    -0.40
     Burgen
    -0.39
    usercontent
    -0.39
     Diener
    -0.37
     Tar
    -0.37
     Mauer
    -0.37
    POSITIVE LOGITS
     XR
    1.67
    XR
    1.63
    XL
    1.62
     XT
    1.60
    XS
    1.59
    XC
    1.58
     XS
    1.58
    XT
    1.54
     XL
    1.54
     XP
    1.52
    Activations Density 0.281%

    No Known Activations