© 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. 9487
    Prev
    Next
    INDEX
    Explanations

    negations in sentences

    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
    omation
    -0.68
     utili
    -0.50
     发表于
    -0.49
    Stain
    -0.49
     facili
    -0.48
      
    -0.47
    agascar
    -0.47
    ovács
    -0.47
    Succes
    -0.46
    Suerte
    -0.46
    POSITIVE LOGITS
     youre
    1.91
     youll
    1.82
     Ive
    1.81
     theyre
    1.80
    Theres
    1.71
     wasnt
    1.70
     Theres
    1.69
     theres
    1.63
     cant
    1.63
     hes
    1.63
    Activations Density 0.041%

    No Known Activations