© 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. 41-GEMMASCOPE-RES-16K
    11. 12232
    Prev
    Next
    INDEX
    Explanations

    programming elements related to property management in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.69
     Monfieur
    -0.66
     ſta
    -0.60
     ſtand
    -0.59
     Conſ
    -0.57
     ſche
    -0.57
     purpoſe
    -0.56
     itſelf
    -0.56
     Eſ
    -0.55
     Efq
    -0.54
    POSITIVE LOGITS
    PARAMETER
    0.65
    CONFIGURATION
    0.64
    ENABLED
    0.63
    ATTRIBUTE
    0.63
    PARAMS
    0.63
    ATTRIBUTES
    0.63
    VALIDATION
    0.62
    SUFFIX
    0.60
    PROCESSING
    0.60
    CONTAINER
    0.60
    Activations Density 1.029%

    No Known Activations