© 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. 10501
    Prev
    Next
    INDEX
    Explanations

    references to abstract concepts and existential inquiries

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

    "...thing" or "...thing."

    np_acts-logits-general · gemini-2.0-flash

    such thing

    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
     none
    -0.48
    none
    -0.46
    None
    -0.46
    rans
    -0.43
    ритори
    -0.43
    endwhile
    -0.43
    vyn
    -0.42
    ともに
    -0.41
    CreateModel
    -0.41
    TemporalType
    -0.40
    POSITIVE LOGITS
     thing
    3.78
     THING
    2.85
    thing
    2.79
     things
    2.66
     Thing
    2.66
    Thing
    2.50
     Things
    2.25
    things
    2.20
     THINGS
    2.19
    Things
    2.19
    Activations Density 0.262%

    No Known Activations