© 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. 35-GEMMASCOPE-RES-16K
    11. 10925
    Prev
    Next
    INDEX
    Explanations

    references to societal observations and categorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     legislation
    -1.00
     stuff
    -0.91
    stuff
    -0.81
    legislation
    -0.80
     informasjon
    -0.78
     Legislation
    -0.76
     Stuff
    -0.75
     footage
    -0.75
    Legislation
    -0.72
     advice
    -0.71
    POSITIVE LOGITS
     pieces
    0.74
     calories
    0.60
     Pieces
    0.59
     welds
    0.58
    TypeArgs
    0.57
     liberties
    0.57
     tenets
    0.56
     bits
    0.56
     accolades
    0.56
     photons
    0.56
    Activations Density 1.196%

    No Known Activations