© 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. 34-GEMMASCOPE-RES-16K
    11. 13729
    Prev
    Next
    INDEX
    Explanations

    evaluations of performance and critiques of artistic direction in creative works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curated
    -0.66
     famously
    -0.59
     onboarding
    -0.58
     tropes
    -0.57
     sourced
    -0.57
     outsourced
    -0.57
     incentiv
    -0.55
     messaging
    -0.53
     nuanced
    -0.53
     datasets
    -0.53
    POSITIVE LOGITS
    faßt
    1.21
     mußten
    0.85
     daß
    0.84
     läßt
    0.83
     mußte
    0.81
    wußt
    0.81
     muß
    0.77
     ибо
    0.77
    luß
    0.76
     wuß
    0.74
    Activations Density 2.575%

    No Known Activations