© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13406
    Prev
    Next
    INDEX
    Explanations

    the presence of headers in a document, particularly those formatted as HTML headings

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

    Markdown headings

    np_acts-logits-general · gemini-2.0-flash

    markdown headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    IsMutable
    -0.60
     Brody
    -0.56
    iterranée
    -0.54
     Мексичка
    -0.54
    úblico
    -0.54
     Öffentlichkeit
    -0.53
    opoulos
    -0.52
     modalités
    -0.50
    qtype
    -0.49
    bertura
    -0.48
    POSITIVE LOGITS
    <h2>
    1.59
    ing
    0.82
    <th>
    0.61
    /*
    0.60
     newState
    0.59
    ##
    0.57
     ſte
    0.56
     useState
    0.56
    /*!
    0.56
    __(/*!
    0.55
    Activations Density 0.042%

    No Known Activations