© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1170
    Prev
    Next
    INDEX
    Explanations

    references to health-related behaviors and their impact on lifestyle

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

    "Self" followed by an action/attitude

    np_acts-logits-general · gemini-2.0-flash

    self-perceived social support and religiousness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    cellona
    -0.55
     concernés
    -0.54
    everywhere
    -0.53
    peque
    -0.53
    دانشنامهٔ
    -0.53
     Distributors
    -0.53
     marié
    -0.52
     aprire
    -0.52
     réunis
    -0.51
     frattempo
    -0.51
    POSITIVE LOGITS
     self
    0.78
     perceived
    0.68
     "..\..\
    0.65
     "..\..\..\
    0.64
    self
    0.63
     Self
    0.62
    SELF
    0.61
    ributions
    0.61
    Self
    0.61
     beliefs
    0.61
    Activations Density 1.254%

    No Known Activations