© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 64075
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes related to user interface elements and their statuses

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

    HTML closing tags and delimiters

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    PageModule
    -0.71
     Marín
    -0.71
     vPvB
    -0.69
     bookId
    -0.69
    \{\\
    -0.68
    tagHelperRunner
    -0.65
    AddTagHelper
    -0.64
     noqa
    -0.64
    featureID
    -0.63
    bcryptjs
    -0.63
    POSITIVE LOGITS
    ">
    0.90
    ')}}">
    0.80
    '>
    0.76
    )">
    0.73
    ="#">
    0.71
    '}}>
    0.69
    <td>
    0.69
    }`}>
    0.68
    %">
    0.67
     }}">
    0.66
    Activations Density 0.025%

    No Known Activations