© 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. 30-GEMMASCOPE-RES-16K
    11. 10829
    Prev
    Next
    INDEX
    Explanations

    phrases that question actions or behaviors in political contexts

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

    Followed by the word "what"

    np_acts-logits-general · gemini-2.0-flash

    bush what

    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
    tonode
    -0.49
    subpackage
    -0.49
    forChild
    -0.49
     rhestr
    -0.46
    óta
    -0.44
    hassee
    -0.43
    MetaObject
    -0.43
    ⌐
    -0.42
    onalds
    -0.42
    QPalette
    -0.41
    POSITIVE LOGITS
     what
    2.89
    what
    2.09
     آنچه
    1.59
    What
    1.58
     ceea
    1.49
     ciò
    1.47
     What
    1.45
     WHAT
    1.40
     hvad
    1.39
     mitä
    1.36
    Activations Density 0.935%

    No Known Activations