© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23-GEMMASCOPE-RES-16K
    11. 15961
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to inquiry and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.73
     يتيمه
    -0.70
    oredCriteria
    -0.70
    AxisAlignment
    -0.70
    writeFieldEnd
    -0.65
     Vikipedi
    -0.62
     resourceCulture
    -0.61
     preſent
    -0.61
     للمعارف
    -0.60
    itación
    -0.60
    POSITIVE LOGITS
     determine
    1.69
     figure
    1.68
    figure
    1.30
     determining
    1.28
    determine
    1.28
     Determine
    1.27
     determines
    1.24
     decide
    1.22
    Determine
    1.20
     figuring
    1.17
    Activations Density 0.561%

    No Known Activations