© 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. 10553
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "What" or related interrogative phrases

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

    Questions starting with "What"

    np_acts-logits-general · gemini-2.0-flash

    what questions

    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
     ujednoznacz
    -0.72
    AndEndTag
    -0.71
     disambiguazione
    -0.56
    verwijspagina
    -0.56
    webElementXpaths
    -0.56
    AnchorStyles
    -0.56
    endpush
    -0.55
     ModelExpression
    -0.53
    SequentialGroup
    -0.52
    didSet
    -0.51
    POSITIVE LOGITS
     kind
    0.59
     happens
    0.56
     happened
    0.56
     about
    0.53
     is
    0.52
     are
    0.52
    What
    0.52
     espécie
    0.51
     kinds
    0.48
     do
    0.44
    Activations Density 0.139%

    No Known Activations