© 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. 36-GEMMASCOPE-RES-16K
    11. 5140
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions and judgments about relationships and social situations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     '\\;'
    -0.48
    Specyfikacja
    -0.46
    InputBorder
    -0.46
    Modular
    -0.44
     lecz
    -0.44
    phemy
    -0.44
     geometr
    -0.44
    UrlResolution
    -0.43
     hyö
    -0.43
     ledig
    -0.42
    POSITIVE LOGITS
     hurtful
    0.71
     unprofessional
    0.67
     thoughtless
    0.65
     insensitive
    0.64
     abusive
    0.64
     manipulative
    0.62
     unpleasant
    0.60
     toxic
    0.60
     disrespectful
    0.59
     narcissistic
    0.57
    Activations Density 0.706%

    No Known Activations