© 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. 24-GEMMASCOPE-RES-16K
    11. 1162
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connecting phrases in complex sentences

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

    that connect clauses or ideas

    np_acts-logits-general · gemini-2.0-flash

    connecting contrasting or listing elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    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
    -0.71
    featureID
    -0.68
     ExecuteAsync
    -0.66
     JAXBElement
    -0.66
     незавершена
    -0.66
    StructEnd
    -0.66
    yntaxException
    -0.65
     ErrIntOverflow
    -0.65
    :✨
    -0.64
    GOTREF
    -0.64
    POSITIVE LOGITS
     furthermore
    0.44
     additionally
    0.44
     thus
    0.43
     thereby
    0.42
     Additionally
    0.41
     dále
    0.40
     sağlay
    0.40
     moreover
    0.37
     således
    0.36
     consequently
    0.36
    Activations Density 0.819%

    No Known Activations