© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5072
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and regulations, particularly in the context of healthcare and aviation

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

    safety and security

    np_acts-logits-general · gemini-2.0-flash

    safety and security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
    ıç
    -0.50
    penup
    -0.48
    XmlAccessType
    -0.48
    VIAF
    -0.48
    esModule
    -0.47
    ieuses
    -0.47
    WEBPACK
    -0.46
     DPRD
    -0.46
     verwe
    -0.44
    hoots
    -0.43
    POSITIVE LOGITS
     safety
    3.62
     safe
    3.38
    safety
    3.22
     Safety
    3.12
    Safety
    3.08
    safe
    3.06
     safely
    3.03
     safer
    3.02
     Safe
    2.95
     safest
    2.94
    Activations Density 0.350%

    No Known Activations