© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13348
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the creation or production of something

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

    Follows indefinite article "a"

    np_acts-logits-general · gemini-2.0-flash

    make a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     AssemblyProduct
    -0.74
    __':
    -0.72
    __':
    -0.67
    MLLoader
    -0.64
    MENAFN
    -0.60
    PickerController
    -0.60
    SourceChecksum
    -0.57
     StatelessWidget
    -0.56
    __":
    -0.54
    RTRS
    -0.52
    POSITIVE LOGITS
     contribution
    0.76
     mark
    0.71
     splash
    0.70
     effort
    0.69
     dent
    0.69
     impression
    0.68
     difference
    0.68
     mistake
    0.67
     statement
    0.62
     mess
    0.62
    Activations Density 0.132%

    No Known Activations