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

    Neuronpedia

    APICircuit 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. 2420
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and inquiries directed at the audience

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

    Sentences starting with "you" or "he"

    np_acts-logits-general · gemini-2.0-flash

    you need support

    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
    ISODE
    -0.52
     发表于
    -0.52
    sinon
    -0.50
    Blame
    -0.49
     sorte
    -0.49
     lenker
    -0.49
    CloseOperation
    -0.49
    kurs
    -0.48
     đích
    -0.48
    RegressionTest
    -0.48
    POSITIVE LOGITS
     interested
    0.71
    StoryboardSegue
    0.70
    uestions
    0.69
     spørgsmål
    0.67
    躇
    0.67
    questions
    0.67
     frågor
    0.65
     questions
    0.65
     Interested
    0.65
     intéress
    0.64
    Activations Density 0.119%

    No Known Activations