© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15680
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" and its variations in context

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

    the word "That" at the beginning of sentences or clauses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    The neuron activates strongly for the word "That" at the beginning of a sentence, particularly when it appears to introduce a new thought, transition, or emphatic statement.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    demonstrative references—especially sentence-initial uses that point back to or summarize a prior statement.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -0.36
    literals
    -0.34
     Ursachen
    -0.33
     dní
    -0.33
     treasures
    -0.31
     így
    -0.30
     thus
    -0.30
     constructions
    -0.30
    êtres
    -0.29
    こんなに
    -0.29
    POSITIVE LOGITS
     pesky
    0.83
    zelfde
    0.75
     يتيمه
    0.69
     darn
    0.66
    Datuak
    0.66
    jenige
    0.63
     damned
    0.63
    SourceChecksum
    0.63
     Infórmanos
    0.63
    principalColumn
    0.62
    Activations Density 0.201%

    No Known Activations