© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 9956
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "to."

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

    "To" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    to date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commit
    -0.52
     interact
    -0.52
     take
    -0.51
     slip
    -0.50
     spend
    -0.50
     subscribe
    -0.49
     move
    -0.49
     strike
    -0.48
     hold
    -0.47
     pull
    -0.47
    POSITIVE LOGITS
     gynhyrchwyd
    0.58
    évaluateur
    0.56
     the
    0.53
    ValueStyle
    0.52
    //
    0.49
     linkovi
    0.45
    InitVars
    0.43
     keuze
    0.42
    oa̍t
    0.42
     forState
    0.42
    Activations Density 0.612%

    No Known Activations