© 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. 14372
    Prev
    Next
    INDEX
    Explanations

    references to actions or instructions involving "to" that indicate intention or purpose

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

    the infinitive verb "to" followed by action verbs.

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

    the infinitive marker “to” introducing a verb (i.e., the particle that precedes verbs in infinitive constructions).

    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
    featureID
    -0.44
    "){
    -0.42
    Rohy
    -0.42
    èdia
    -0.41
    []){
    -0.39
     cumplido
    -0.38
     kapturem
    -0.38
     auffi
    -0.38
     heridos
    -0.38
    enumi
    -0.37
    POSITIVE LOGITS
    mals
    0.51
    dotto
    0.49
    which
    0.49
     Willard
    0.48
    textStyle
    0.48
    findpost
    0.47
    cherie
    0.47
     which
    0.46
    BitConverter
    0.46
    ly
    0.46
    Activations Density 0.430%

    No Known Activations