© 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 EvalsExportsAPI 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. 8731
    Prev
    Next
    INDEX
    Explanations

    terminology related to research initiatives and organizational structures in healthcare and science

    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
     probably
    -0.47
    arschijnlijk
    -0.44
    probably
    -0.44
     Probably
    -0.43
    readlines
    -0.43
     beginnetje
    -0.43
    gbaar
    -0.42
     zdar
    -0.42
    Shouldn
    -0.42
     Besoin
    -0.42
    POSITIVE LOGITS
     lever
    0.98
     fur
    0.76
     addresses
    0.75
     supports
    0.74
     implements
    0.71
     harnesses
    0.70
     optim
    0.68
     advances
    0.67
     dep
    0.65
     seeks
    0.65
    Activations Density 0.498%

    No Known Activations