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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1432
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or potential outcomes in a political or business context

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

    Follows "If" or signals conditionality

    np_acts-logits-general · gemini-2.0-flash

    if, then clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quase
    -0.43
     telah
    -0.42
     almost
    -0.41
    可是
    -0.38
     hampir
    -0.37
     schonmal
    -0.36
     Ensino
    -0.36
     nearly
    -0.36
     prawie
    -0.36
     corresponded
    -0.36
    POSITIVE LOGITS
    このまま
    0.64
     nanti
    0.63
    principalTable
    0.60
    無事に
    0.60
     continue
    0.60
     successful
    0.59
     decides
    0.58
     eventual
    0.56
    TagMode
    0.56
     future
    0.56
    Activations Density 0.455%

    No Known Activations