© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7178
    Prev
    Next
    INDEX
    Explanations

    patterns of formatting or structural elements within text

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

    Text preceding a section number

    np_acts-logits-general · gemini-2.0-flash

    English, 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
    aarrggbb
    -0.86
    OGND
    -0.86
     Италијани
    -0.81
    InvalidProtocol
    -0.79
    ########.
    -0.75
    sizeCache
    -0.71
    Personensuche
    -0.71
    Parcelize
    -0.71
     ویکی‌پدی
    -0.71
    (!__
    -0.70
    POSITIVE LOGITS
     tanong
    0.44
     entertained
    0.44
     ympä
    0.42
    Naissance
    0.41
     cue
    0.41
     näky
    0.40
    σιμοποι
    0.40
    langsung
    0.40
     palk
    0.39
    DeviceType
    0.39
    Activations Density 0.033%

    No Known Activations