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. 1584
    Prev
    Next
    INDEX
    Explanations

    strategies and actions for effective communication and engagement within organizations

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

    Imperative form of verbs

    np_acts-logits-general · gemini-2.0-flash

    directive verbs for yourself

    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
    migrationBuilder
    -0.84
     presumably
    -0.65
     незавершена
    -0.64
     jsPsych
    -0.64
    WithIOException
    -0.62
     StatelessWidget
    -0.60
    quite
    -0.60
     Presumably
    -0.58
     vermutlich
    -0.58
    almost
    -0.58
    POSITIVE LOGITS
     yourself
    0.90
     thyself
    0.78
     Yourself
    0.77
    yourself
    0.76
     thật
    0.69
     YOURSELF
    0.68
     Chwiliwch
    0.66
     oneself
    0.65
     yourselves
    0.64
     möglichst
    0.63
    Activations Density 0.348%

    No Known Activations