© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7465
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" and related conjunctions

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

    Follows the word "that"

    np_acts-logits-general · gemini-2.0-flash

    that clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    them
    -0.83
    Them
    -0.76
     THEM
    -0.76
     itſelf
    -0.74
     propOrder
    -0.69
     Itself
    -0.67
     alfo
    -0.67
     Them
    -0.67
     sayin
    -0.65
     Shakspeare
    -0.65
    POSITIVE LOGITS
     although
    1.64
     while
    1.56
     despite
    1.49
     there
    1.46
     when
    1.44
     since
    1.29
     if
    1.23
     the
    1.20
     during
    1.17
    although
    1.15
    Activations Density 0.525%

    No Known Activations