© 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. 11417
    Prev
    Next
    INDEX
    Explanations

    future intentions and plans

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

    the phrase "will see" or similar constructions expressing future uncertainty or anticipation.

    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
    RenderAtEndOf
    -0.70
    tagHelperRunner
    -0.68
     ब्रेकडाउन
    -0.67
     препратки
    -0.64
    ########.
    -0.62
     समीक्षक
    -0.62
    setVerticalGroup
    -0.61
    AsUp
    -0.60
     springfox
    -0.60
     otomatig
    -0.60
    POSITIVE LOGITS
     see
    1.75
    see
    1.45
     See
    1.41
    See
    1.38
     sees
    1.19
    看看
    1.16
     xem
    1.12
     SEE
    1.11
     seeing
    1.08
     ببین
    1.05
    Activations Density 0.284%

    No Known Activations