© 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. 18-GEMMASCOPE-RES-16K
    11. 3549
    Prev
    Next
    INDEX
    Explanations

    phrases related to awareness of health risks and preventative measures

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

    health, safety, and prevention

    np_acts-logits-general · gemini-2.0-flash

    preventable actions and behaviors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.77
    Personensuche
    -0.72
    RegressionTest
    -0.69
    MessageOf
    -0.65
    OGND
    -0.64
    findpost
    -0.63
    +#+#
    -0.61
    GEBURTSDATUM
    -0.61
    rawDesc
    -0.61
     MenuView
    -0.61
    POSITIVE LOGITS
     ciudadanía
    0.72
     comportements
    0.65
    Know
    0.64
     preventable
    0.63
     télécharge
    0.59
     Know
    0.58
     prévention
    0.57
     prevention
    0.57
     domésticos
    0.56
     gestes
    0.55
    Activations Density 0.187%

    No Known Activations