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. 16-GEMMASCOPE-RES-16K
    6. 1660
    Prev
    Next
    INDEX
    Explanations

    phrases that express collective agreement or shared sentiments among individuals

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

    'everybody' and 'everyone'

    np_acts-logits-general · gemini-2.0-flash

    Everybody/everyone/all followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GNA
    -0.61
    té
    -0.57
    CloseOperation
    -0.57
     Ground
    -0.55
    cba
    -0.55
    częściej
    -0.55
    BagConstraints
    -0.54
    "/",
    -0.53
    Fli
    -0.53
     xuyên
    -0.52
    POSITIVE LOGITS
     Everybody
    0.96
    Everybody
    0.93
     everybody
    0.92
    everybody
    0.91
     Everyone
    0.91
     everyone
    0.89
    Everyone
    0.88
    everyone
    0.88
     EVERYONE
    0.82
     beginnetje
    0.68
    Activations Density 0.146%

    No Known Activations