© 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. 4878
    Prev
    Next
    INDEX
    Explanations

    names or identifiers related to people, particularly in a scientific or academic context

    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
    ii
    -0.87
    iiiiiiii
    -0.76
    iii
    -0.75
    iiiii
    -0.73
    iiii
    -0.73
    iit
    -0.58
    iin
    -0.57
    змом
    -0.55
    اں
    -0.53
    mages
    -0.51
    POSITIVE LOGITS
     ujednoznacz
    0.44
    awtextra
    0.40
    invokeLater
    0.36
    Numerology
    0.36
    &__
    0.36
    scheduled
    0.35
    UnknownFieldSet
    0.35
    specify
    0.34
     て
    0.33
    swimming
    0.33
    Activations Density 0.172%

    No Known Activations