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. 20-GEMMASCOPE-RES-16K
    6. 889
    Prev
    Next
    INDEX
    Explanations

    information related to people expressing emotions or desires

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

    Followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    verbs related to wanting and receiving

    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
     ویکی‌پدیا
    -0.93
     myself
    -0.92
    GEBURTSDATUM
    -0.91
     yourself
    -0.85
     oneself
    -0.84
    myself
    -0.79
     transfieras
    -0.78
    yourself
    -0.75
    WillAppear
    -0.74
     ModelExpression
    -0.73
    POSITIVE LOGITS
     us
    0.73
     me
    0.58
     нас
    0.54
     you
    0.54
     للمعارف
    0.50
     bizi
    0.49
     plaintiffs
    0.48
    ukų
    0.47
    くださ
    0.47
    IBarButtonItem
    0.47
    Activations Density 0.593%

    No Known Activations