© 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. 6851
    Prev
    Next
    INDEX
    Explanations

    connections and conditions described in a problem or requirement

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

    Followed by "there" or "There"

    np_acts-logits-general · gemini-2.0-flash

    questions asking "is there"

    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
    WebVitals
    -0.60
    MarshalTo
    -0.55
    ----</
    -0.54
    вість
    -0.51
     unknownFields
    -0.50
    GeneratedValue
    -0.48
     wszystkim
    -0.47
    Jäh
    -0.47
    まさか
    -0.46
    EDEFAULT
    -0.46
    POSITIVE LOGITS
     there
    3.60
    there
    2.89
     There
    2.65
    There
    2.59
     THERE
    2.55
    THERE
    2.22
     هناك
    1.90
     theres
    1.72
    theres
    1.68
    Theres
    1.45
    Activations Density 0.581%

    No Known Activations