© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 356
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sexual abuse, particularly involving children or minors.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    references to sexual abuse cases involving minors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sexual abuse or misconduct

    np_acts-logits-general · gemini-2.0-flash

    sexual abuse and molestation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    réhen
    -0.33
     regiões
    -0.29
     (
    -0.29
     variedades
    -0.29
     senhora
    -0.29
    แต่
    -0.28
     среднем
    -0.27
     dále
    -0.27
     puentes
    -0.26
    ური
    -0.26
    POSITIVE LOGITS
    ſelf
    0.79
     ſte
    0.76
     itſelf
    0.76
     Monfieur
    0.73
     Jefus
    0.73
     ſind
    0.71
     pleaſure
    0.71
     myſelf
    0.71
    ſhip
    0.70
     sexual
    0.69
    Activations Density 0.167%

    No Known Activations