© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 8553
    Prev
    Next
    INDEX
    Explanations

    references to the Maine Department of Corrections and the jail system

    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
     Dolores
    -0.44
     Alve
    -0.43
     Mississauga
    -0.39
    Clr
    -0.38
     Kernel
    -0.36
     Krypton
    -0.36
     Humber
    -0.36
     Gauteng
    -0.36
     nomin
    -0.35
    isabeth
    -0.35
    POSITIVE LOGITS
    Maine
    1.32
     Maine
    1.32
     maine
    1.03
     Bangor
    0.90
    maine
    0.79
    Portland
    0.74
     Portland
    0.74
    OGND
    0.73
    缅
    0.71
     lobster
    0.68
    Activations Density 0.137%

    No Known Activations