© 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. 9833
    Prev
    Next
    INDEX
    Explanations

    references to financial institutions and banking services

    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
     المعيارى
    -0.54
    хьтан
    -0.50
     disambiguazione
    -0.49
    SharedCtor
    -0.47
     pinch
    -0.42
    msgTypes
    -0.42
     intptr
    -0.42
    المكان
    -0.42
    tangentMode
    -0.40
     Roskov
    -0.39
    POSITIVE LOGITS
     branches
    0.85
     branch
    0.84
     Branch
    0.79
     Branches
    0.79
    Branch
    0.75
     BRANCH
    0.75
    branch
    0.73
    Branches
    0.72
    branches
    0.68
    BRANCH
    0.67
    Activations Density 0.219%

    No Known Activations