© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103851
    Prev
    Next
    INDEX
    Explanations

    probabilities associated with drawing items from a set without replacement

    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
    options
    -0.36
    SuppressLint
    -0.35
     options
    -0.35
    seku
    -0.33
    Ste
    -0.33
     gelt
    -0.33
     Obra
    -0.31
     ブルゾン
    -0.31
    atriz
    -0.31
     ste
    -0.31
    POSITIVE LOGITS
    AndEndTag
    0.59
    RegressionTest
    0.55
     CreateTagHelper
    0.55
    canActivate
    0.55
     мәкал
    0.53
    archiviato
    0.53
    بوابة
    0.52
    GEBURTSDATUM
    0.52
    MessageOf
    0.52
    RTEX
    0.52
    Activations Density 0.176%

    No Known Activations