© 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. 6211
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and user-driven choices or preferences

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

    conditional phrases with "as" that express manner or degree (e.g., "as you see fit", "as desired", "as many as").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     expecting
    -0.38
     hopes
    -0.36
     esperaba
    -0.36
     dovrebbero
    -0.35
    Expecting
    -0.35
    colgroup
    -0.34
     Hopes
    -0.33
     hoping
    -0.32
    writerow
    -0.32
     Expect
    -0.32
    POSITIVE LOGITS
     deemed
    0.75
     deem
    0.69
     deems
    0.68
     appropriate
    0.65
     pleases
    0.63
    deemed
    0.63
    URLException
    0.62
     пожела
    0.61
     whim
    0.61
     Wicidata
    0.59
    Activations Density 0.306%

    No Known Activations