Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13564
    Prev
    Next
    INDEX
    Explanations

    references to programming schedules and show premieres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.67
    JdbcTemplate
    -0.49
    audi
    -0.49
    yelidikan
    -0.48
    مرا
    -0.48
    playlists
    -0.47
    ExecuteReader
    -0.47
    Audiences
    -0.47
     Futsal
    -0.47
     bestaan
    -0.47
    POSITIVE LOGITS
     recent
    0.89
     notable
    0.87
     entries
    0.83
     notables
    0.83
     examples
    0.83
     listed
    0.80
    recent
    0.80
     contenders
    0.80
     featured
    0.79
     noteworthy
    0.78
    Activations Density 0.383%

    No Known Activations