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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 5193
    Prev
    Next
    INDEX
    Explanations

    elements related to social interaction and community dynamics

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

    preceding "to"

    np_acts-logits-general · gemini-2.0-flash

    important to be

    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
    chafts
    -0.54
     N
    -0.52
    *>(
    -0.51
     disambiguazione
    -0.50
     E
    -0.50
    Diweddarwch
    -0.48
     *>(
    -0.48
    ]+=
    -0.46
     B
    -0.46
     Green
    -0.45
    POSITIVE LOGITS
    principalTable
    0.76
    ValueStyle
    0.74
     itſelf
    0.73
     myſelf
    0.73
     Efq
    0.72
     estekak
    0.62
    Билгалдахарш
    0.61
     eyelashes
    0.61
     Limoges
    0.60
     Ciro
    0.60
    Activations Density 0.341%

    No Known Activations