© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5796
    Prev
    Next
    INDEX
    Explanations

    HTML markup tags indicating structure or headings in documents

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

    Section headers and figure captions

    np_acts-logits-general · gemini-2.0-flash

    methods

    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
     Tar
    -0.53
     lot
    -0.53
    Читати
    -0.52
     ro
    -0.50
    ushan
    -0.50
     Mul
    -0.49
     #
    -0.49
    illos
    -0.49
     bar
    -0.49
    ']/
    -0.48
    POSITIVE LOGITS
     الحره
    0.77
     متعلقه
    0.73
    RenderAtEndOf
    0.73
     مرئيه
    0.70
     referenties
    0.69
    __":
    
    0.69
     kasarigan
    0.69
     مشين
    0.69
    ंदीखरीदारी
    0.68
    principalTable
    0.67
    Activations Density 0.052%

    No Known Activations