© 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. 4400
    Prev
    Next
    INDEX
    Explanations

    expressions that convey uncertainty or inquiries about experiences

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

    "it" followed by "takes" or a related word

    np_acts-logits-general · gemini-2.0-flash

    what it takes

    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
    DoubleQuotes
    -0.79
    UnknownFields
    -0.74
    YTICAL
    -0.65
    Бахар
    -0.55
     linkovi
    -0.55
     Grenzen
    -0.54
    ConfigureAwait
    -0.53
     AssemblyCulture
    -0.53
    thenia
    -0.52
    γη
    -0.52
    POSITIVE LOGITS
     takes
    0.77
    takes
    0.75
     Takes
    0.68
    Takes
    0.66
     required
    0.64
    KURZBESCHREIBUNG
    0.60
    required
    0.59
     it
    0.58
     requires
    0.58
     تانيه
    0.57
    Activations Density 0.117%

    No Known Activations