© 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. 15823
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names

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

    appearing at the beginning of words

    np_acts-logits-general · gemini-2.0-flash

    prefixes of entities with long s spellings

    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
     
    -0.73
    ,
    -0.66
     (
    -0.60
     base
    -0.60
     in
    -0.59
    thenReturn
    -0.59
    :
    -0.56
    .
    -0.55
     of
    -0.55
     set
    -0.54
    POSITIVE LOGITS
    ſelf
    1.10
    ſelves
    1.02
     queſta
    0.99
     Diſ
    0.98
     handker
    0.98
     Anſ
    0.98
     ་་
    0.95
     Forumite
    0.94
     ſind
    0.93
     ſever
    0.92
    Activations Density 0.545%

    No Known Activations