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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11357
    Prev
    Next
    INDEX
    Explanations

    terms related to safety protocols and hygiene practices

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

    safety and precautions

    np_acts-logits-general · gemini-2.0-flash

    health and hygiene advice

    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
     resourceCulture
    -0.61
    esModule
    -0.54
     lenker
    -0.50
     estimés
    -0.49
    enfance
    -0.48
     urgencia
    -0.48
    眠
    -0.46
    UNLOCK
    -0.46
     woken
    -0.45
    obacz
    -0.45
    POSITIVE LOGITS
     saniti
    0.98
     sanitize
    0.94
     distancing
    0.92
     social
    0.89
     sanitized
    0.88
    DeleteBehavior
    0.87
     socially
    0.87
     distanciation
    0.87
     hygiene
    0.85
     hygienic
    0.82
    Activations Density 0.048%

    No Known Activations