© 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. 24-GEMMASCOPE-RES-16K
    11. 4601
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions and transitional phrases in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "but" and its surrounding context

    np_acts-logits-general · gemini-2.0-flash

    but that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.66
     fubject
    -0.60
     purpoſe
    -0.57
     itſelf
    -0.56
     ſind
    -0.50
     occaf
    -0.50
     poffe
    -0.50
     ſeveral
    -0.49
     Diſ
    -0.49
     abſ
    -0.49
    POSITIVE LOGITS
     I
    0.55
     yeah
    0.49
     it
    0.49
    but
    0.48
     But
    0.47
    everything
    0.47
     but
    0.46
    But
    0.44
     we
    0.43
    yeah
    0.43
    Activations Density 0.160%

    No Known Activations