© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104203
    Prev
    Next
    INDEX
    Explanations

    scientific measurements and terms related to data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     estekak
    -0.76
    LookAnd
    -0.75
    󠁢
    -0.71
     autorytatywna
    -0.71
     queſta
    -0.70
    <unused14>
    -0.69
     ब्रेकडाउन
    -0.69
    <unused79>
    -0.69
    <unused68>
    -0.69
    <unused52>
    -0.69
    POSITIVE LOGITS
    I
    0.35
     науки
    0.34
     I
    0.34
     (
    0.33
     Tag
    0.33
     Hunt
    0.32
     Bak
    0.32
     W
    0.32
    ito
    0.32
     {
    0.32
    Activations Density 0.135%

    No Known Activations