© 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-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10572
    Prev
    Next
    INDEX
    Explanations

    references to the PR RSV virus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Alpes
    -0.59
     Amen
    -0.53
    hip
    -0.53
    anap
    -0.52
     assemb
    -0.52
    thig
    -0.51
    ורה
    -0.51
    parsedMessage
    -0.50
     Krug
    -0.50
    くださいませ
    -0.50
    POSITIVE LOGITS
    %)$
    1.02
    rungsseite
    0.96
    ymce
    0.90
     próprios
    0.75
     blessés
    0.72
    AndEndTag
    0.68
     PR
    0.68
     quæ
    0.67
     pauvres
    0.67
     próprias
    0.65
    Activations Density 0.055%

    No Known Activations