© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11841
    Prev
    Next
    INDEX
    Explanations

    phrases related to weaponry and defense mechanisms

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Accent
    -0.39
    idyl
    -0.39
     occupé
    -0.38
     Accent
    -0.37
    っこう
    -0.36
     energ
    -0.36
    ❮
    -0.36
     Conti
    -0.35
     WHE
    -0.35
    pea
    -0.35
    POSITIVE LOGITS
     resistant
    0.70
     CreateTagHelper
    0.66
     résistance
    0.61
     resistance
    0.60
     kasarigan
    0.59
     Resistant
    0.59
     defences
    0.58
     surla
    0.57
     resists
    0.57
     resisting
    0.57
    Activations Density 0.582%

    No Known Activations