© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15023
    Prev
    Next
    INDEX
    Explanations

    HTML and web page structure elements

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

    HTML tags: p and span

    np_acts-logits-general · gemini-2.0-flash

    HTML paragraphs and spans

    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
     فريبيس
    -0.98
    таратура
    -0.90
     препратки
    -0.76
     FetchType
    -0.71
    TemporalType
    -0.69
     internetowa
    -0.69
    protoimpl
    -0.69
     كومونز
    -0.67
    Література
    -0.67
    ConstraintMaker
    -0.66
    POSITIVE LOGITS
    ("")]
    0.56
    <tr>
    0.53
    ><
    0.53
    "><
    0.52
    $$\
    0.51
    <eos>
    0.51
    block
    0.49
    ↵↵↵↵↵
    0.48
    <blockquote>
    0.47
     Block
    0.47
    Activations Density 0.141%

    No Known Activations