© 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. 5338
    Prev
    Next
    INDEX
    Explanations

    the word "In" and its various occurrences and contexts in the text

    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
    withstanding
    -1.24
    structors
    -1.16
    quiries
    -1.04
    которые
    -1.00
    itudinal
    -0.97
    corpor
    -0.96
    volvement
    -0.96
    hibition
    -0.95
    ergies
    -0.94
    sects
    -0.92
    POSITIVE LOGITS
    herited
    0.85
    hogy
    0.82
    ertia
    0.82
    tualmente
    0.81
    guien
    0.77
    consistency
    0.69
    noons
    0.68
    formazioni
    0.68
    verted
    0.65
    bound
    0.57
    Activations Density 0.308%

    No Known Activations