© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105245
    Prev
    Next
    INDEX
    Explanations

    terms related to lighting technologies and their applications

    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
    fold
    -0.38
    FOLD
    -0.37
     Autorizaciones
    -0.36
    sun
    -0.35
     logica
    -0.33
     ब्रेकडाउन
    -0.33
     rica
    -0.33
     champignons
    -0.33
     링
    -0.32
    db
    -0.32
    POSITIVE LOGITS
    yntaxException
    0.61
    CppMethod
    0.45
     wireType
    0.45
    "}";
    0.44
    tagHelperRunner
    0.44
    ViewInit
    0.44
    OGND
    0.42
     تكبرها
    0.41
     emit
    0.41
    featureID
    0.40
    Activations Density 0.081%

    No Known Activations