© 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. 15221
    Prev
    Next
    INDEX
    Explanations

    references to notable musicians and composers in various contexts

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

    Preceding words in titles or names

    np_acts-logits-general · gemini-2.0-flash

    names of musicians and athletes

    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
    PreferredItem
    -0.61
     vPvB
    -0.51
    écoute
    -0.51
    )++;
    -0.51
    idać
    -0.50
    Personendaten
    -0.50
    createServer
    -0.47
     Мексичка
    -0.47
    InsertCommand
    -0.46
     midwife
    -0.45
    POSITIVE LOGITS
    libft
    0.78
     himself
    0.74
     Memorial
    0.73
    Przypisy
    0.69
     persönlich
    0.64
    Iné
    0.64
     Foundation
    0.62
    TRIBUTE
    0.62
     &
    0.59
     fans
    0.58
    Activations Density 0.223%

    No Known Activations