© 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. 13152
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific formatting marker or signal indicating the start of a section or segment in the text

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

    following initials/single letters

    np_acts-logits-general · gemini-2.0-flash

    foreign language words

    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
     &
    -0.66
    ,
    -0.62
     mo
    -0.61
    ிகள்
    -0.59
     dan
    -0.56
     (
    -0.55
     ?>/
    -0.55
     sur
    -0.54
    /
    -0.54
    (
    -0.53
    POSITIVE LOGITS
     iſt
    0.96
     مشين
    0.92
    ésult
    0.90
     ujednoznacz
    0.89
     ſind
    0.86
    σθαι
    0.84
    ſelves
    0.84
    abestanden
    0.81
    BibitemShut
    0.80
    felves
    0.80
    Activations Density 0.037%

    No Known Activations