© 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. 0-GEMMASCOPE-RES-16K
    11. 4103
    Prev
    Next
    INDEX
    Explanations

    references to various types of abuse, particularly sexual and child abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avoient
    -0.78
    PreferredItem
    -0.70
     '\\;'
    -0.67
     miniaturka
    -0.66
     ainfi
    -0.66
     étoient
    -0.65
     Wikiseite
    -0.65
     démocr
    -0.63
     itſelf
    -0.63
     democrática
    -0.63
    POSITIVE LOGITS
     He
    0.71
     She
    0.69
     Mah
    0.66
    His
    0.65
    Show
    0.64
     His
    0.62
     his
    0.61
     They
    0.61
    Mah
    0.60
     We
    0.60
    Activations Density 0.625%

    No Known Activations