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. 3125
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and their variations in context

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

    Contractions of "are" followed by adjectives or adverbs

    np_acts-logits-general · gemini-2.0-flash

    if you are

    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
    styleType
    -0.70
     saites
    -0.70
    IVEREF
    -0.66
    delwed
    -0.62
    Autoritní
    -0.61
    كويكب
    -0.59
    下载附件
    -0.58
    classnames
    -0.58
    usercontent
    -0.58
     nakalista
    -0.57
    POSITIVE LOGITS
     planning
    0.85
    planning
    0.70
     new
    0.65
     intending
    0.64
     wondering
    0.62
    Planning
    0.61
     thinking
    0.60
     Planning
    0.59
     trying
    0.59
     hoping
    0.57
    Activations Density 0.197%

    No Known Activations