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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5805
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but" or similar transitional phrases indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ravi
    -0.64
     Waray
    -0.61
    baya
    -0.60
     Litu
    -0.60
     Aire
    -0.60
    necked
    -0.59
    KeyName
    -0.56
     linden
    -0.55
     projective
    -0.55
    voo
    -0.55
    POSITIVE LOGITS
     but
    3.60
     But
    3.35
    But
    3.15
     pero
    3.07
    but
    3.06
     BUT
    2.88
     nhưng
    2.68
     tetapi
    2.61
    但
    2.60
    BUT
    2.51
    Activations Density 0.215%

    No Known Activations