© 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. 40-GEMMASCOPE-RES-16K
    11. 7628
    Prev
    Next
    INDEX
    Explanations

    key attributes and qualities of creative individuals and their work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.53
    DBNull
    -0.45
     Wikimedijinoj
    -0.44
    jsxFileName
    -0.43
     المعيارى
    -0.42
    FormTagHelper
    -0.40
     Spisak
    -0.40
    tonode
    -0.39
    otriva
    -0.39
     epiz
    -0.38
    POSITIVE LOGITS
     explore
    0.82
     infuse
    0.80
     capture
    0.75
     explores
    0.73
     fusing
    0.71
     reinterpret
    0.70
     translate
    0.70
     exploring
    0.69
     interpret
    0.68
     incorporate
    0.67
    Activations Density 0.327%

    No Known Activations