© 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. 22-GEMMASCOPE-RES-16K
    11. 14231
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Although" and its variations, indicating contrasting or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.67
     itſelf
    -0.63
     disambiguazione
    -0.55
     Kiran
    -0.55
     Samaria
    -0.55
     issuer
    -0.53
    ptid
    -0.53
     RVA
    -0.52
    ſelf
    -0.50
     ſte
    -0.50
    POSITIVE LOGITS
    though
    0.91
    Though
    0.80
     Though
    0.79
     though
    0.79
     THOUGH
    0.76
    although
    0.70
    ांकि
    0.69
     although
    0.67
    ewel
    0.65
    Aunque
    0.63
    Activations Density 0.103%

    No Known Activations