© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 7588
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.77
     ſever
    -0.75
     raiſ
    -0.72
     Houſe
    -0.71
     anſ
    -0.71
     ſta
    -0.69
    LookAnd
    -0.69
     ſol
    -0.68
     Inſ
    -0.68
    msgTypes
    -0.68
    POSITIVE LOGITS
     that
    2.20
    that
    1.63
     THAT
    1.56
     That
    1.54
    That
    1.47
    THAT
    1.40
     bahwa
    1.16
     bahawa
    1.09
     thats
    1.09
     que
    1.03
    Activations Density 0.546%

    No Known Activations