© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6818
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to safety and protective measures

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

    providing safety or defense

    np_acts-logits-general · gemini-2.0-flash

    protection and defense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.55
    évaluateur
    -0.55
    moveToFirst
    -0.52
    quelize
    -0.49
    mények
    -0.48
    +:+
    -0.47
    ContentAsync
    -0.47
    SourceChecksum
    -0.47
    UrlResolution
    -0.46
     parseFrom
    -0.46
    POSITIVE LOGITS
     protection
    3.17
     Protection
    2.78
     protect
    2.75
     protecting
    2.74
    protection
    2.73
    Protection
    2.64
     protects
    2.57
     protective
    2.52
     PROTECTION
    2.50
     Protect
    2.50
    Activations Density 0.594%

    No Known Activations