© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1925
    Prev
    Next
    INDEX
    Explanations

    the character "Cha" in various forms related to a specific subject or theme

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

    cha followed by other letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     itſelf
    -0.86
     uſed
    -0.80
     ſtate
    -0.78
     purpoſe
    -0.78
     cauſe
    -0.77
     myſelf
    -0.75
    enterOuterAlt
    -0.73
     themſelves
    -0.73
     ſtand
    -0.73
    ="">
    -0.73
    POSITIVE LOGITS
     cha
    0.85
     Cha
    0.79
    Cha
    0.78
    cha
    0.57
     CHAP
    0.52
    Chap
    0.50
     CHAM
    0.48
     chameleon
    0.47
     Chá
    0.46
     Ча
    0.44
    Activations Density 0.009%

    No Known Activations