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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8803
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "PR" which likely represents "Public Relations" or a related concept in medical or scientific contexts

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

    starting with "pr"

    np_acts-logits-general · gemini-2.0-flash

    prefix 'pr'

    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
    AnchorStyles
    -0.81
    TagMode
    -0.73
     désolés
    -0.71
    ISupport
    -0.68
    لينكات
    -0.68
    Enllaces
    -0.68
    rophes
    -0.68
    ValueStyle
    -0.66
    principalTable
    -0.64
    رشف
    -0.62
    POSITIVE LOGITS
     Huskies
    0.52
     soutě
    0.49
     tracción
    0.46
     belangrij
    0.45
     eneste
    0.45
    AddField
    0.44
    tsburgh
    0.43
    r
    0.43
    pr
    0.42
     कथ
    0.42
    Activations Density 0.186%

    No Known Activations