© 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. 31-GEMMASCOPE-RES-16K
    11. 3046
    Prev
    Next
    INDEX
    Explanations

    concerns related to privacy and personal beliefs

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    negative or objectionable statements about social norms and restrictions.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Aiheesta
    -0.42
    EMBER
    -0.39
     Manfaat
    -0.39
     StatefulWidget
    -0.38
    fern
    -0.37
     Komunikasi
    -0.37
    กุ
    -0.37
    wezen
    -0.37
    DispatchToProps
    -0.36
    WSGI
    -0.35
    POSITIVE LOGITS
     bothers
    1.09
     annoys
    1.09
     excites
    1.01
     fascin
    0.94
     scares
    0.93
     bothering
    0.88
     annoy
    0.85
     infuri
    0.82
     frighten
    0.81
     bother
    0.80
    Activations Density 0.472%

    No Known Activations