© 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 EvalsExportsAPI 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. 8064
    Prev
    Next
    INDEX
    Explanations

    phrases related to online safety and extremist content moderation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     poor
    -0.37
     par
    -0.34
     Por
    -0.33
     port
    -0.31
     board
    -0.31
     bre
    -0.30
     Plan
    -0.30
    ViewFeatures
    -0.30
     Class
    -0.30
     Poor
    -0.29
    POSITIVE LOGITS
    twimg
    0.71
     algorithmic
    0.68
    UserScript
    0.63
     ब्रेकडाउन
    0.60
    majánló
    0.60
    IntoConstraints
    0.59
    pecabe
    0.59
     removals
    0.58
     algoritmo
    0.58
    algorithmic
    0.58
    Activations Density 0.318%

    No Known Activations