© 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. 22-GEMMASCOPE-RES-16K
    11. 3956
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming constructs related to object-oriented programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    可
    -0.32
     grado
    -0.32
    PERATURE
    -0.30
     nature
    -0.30
    fär
    -0.29
     women
    -0.29
     style
    -0.28
    ẤT
    -0.27
     presidenta
    -0.27
     tra
    -0.27
    POSITIVE LOGITS
    SharedCtor
    0.80
    SharedDtor
    0.74
    stdc
    0.71
    featureID
    0.71
    principalColumn
    0.69
     surla
    0.69
    OGND
    0.68
    balleur
    0.66
     EconPapers
    0.66
    <unused74>
    0.65
    Activations Density 0.676%

    No Known Activations