© 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. 3642
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "As" and its variations to indicate examples or references in explanations

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

    Follows the word "as"

    np_acts-logits-general · gemini-2.0-flash

    as followed by pronoun or description

    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
    encodeWith
    -0.86
    rrggbb
    -0.80
    alyptus
    -0.71
    routeProvider
    -0.69
    TagMode
    -0.65
    ObjectContext
    -0.64
    qrstuvwxyz
    -0.64
     AttributeSet
    -0.64
    Papier
    -0.63
    YMMV
    -0.62
    POSITIVE LOGITS
     already
    0.59
     compared
    0.56
     stated
    0.54
     متعلقه
    0.53
     regards
    0.53
     known
    0.52
     mentioned
    0.52
     redan
    0.50
     shown
    0.49
     learnt
    0.49
    Activations Density 0.165%

    No Known Activations