© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7579
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate negation or uncertainty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    almost
    -0.68
     Almost
    -0.65
    Almost
    -0.64
     almost
    -0.61
     hampir
    -0.58
     quase
    -0.57
    ThroughAttribute
    -0.56
     piuttosto
    -0.54
     scarcely
    -0.54
     հղումներ
    -0.54
    POSITIVE LOGITS
     necessarily
    1.72
     necessariamente
    1.33
     necesariamente
    1.32
    necessarily
    1.30
     nécessairement
    1.12
     unbedingt
    0.96
     Necess
    0.91
     always
    0.90
     forcément
    0.90
     nødvendig
    0.89
    Activations Density 1.170%

    No Known Activations