© 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. 14-GEMMASCOPE-RES-16K
    11. 10195
    Prev
    Next
    INDEX
    Explanations

    references to legal testimony and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.68
    WebElementEntity
    -0.67
     ujednoznacz
    -0.63
    convenience
    -0.60
    opsida
    -0.58
    IsMutable
    -0.58
    Тогда
    -0.58
     convenience
    -0.58
    opsis
    -0.56
    方便
    -0.55
    POSITIVE LOGITS
    FromArgb
    0.53
     finale
    0.48
    SequentialGroup
    0.46
     riuscito
    0.46
     descended
    0.46
     indruk
    0.46
    Overall
    0.46
    __[
    0.45
     saites
    0.45
     calldata
    0.45
    Activations Density 0.575%

    No Known Activations