© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 22824
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "perhaps" in various forms to indicate uncertainty or speculation

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

    introducing possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nigger
    -0.58
     billy
    -0.58
    billy
    -0.58
    +#+#
    -0.57
    talk
    -0.56
    BILL
    -0.55
    ML
    -0.54
     Houſe
    -0.53
     devaluation
    -0.53
     Nationality
    -0.52
    POSITIVE LOGITS
     perhaps
    0.82
    perhaps
    0.75
     Perhaps
    0.70
    Perhaps
    0.63
    jména
    0.63
    mektedir
    0.63
     quizás
    0.62
    maktadır
    0.54
    ktır
    0.53
    melidir
    0.53
    Activations Density 0.030%

    No Known Activations