© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 95275
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or speculation expressed through the word "suppose"

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

    phrases starting with suppose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ethnic
    -0.51
    NewReader
    -0.49
     Racism
    -0.47
    endregion
    -0.47
     насељу
    -0.46
     Elev
    -0.46
    Marital
    -0.45
     виправивши
    -0.45
    City
    -0.45
     nakalista
    -0.45
    POSITIVE LOGITS
     suppose
    1.77
     Suppose
    1.29
    Suppose
    1.27
     supposes
    1.15
     supposing
    0.91
     suppos
    0.80
    sup
    0.79
     supposition
    0.77
     supposed
    0.73
     supone
    0.69
    Activations Density 0.020%

    No Known Activations