© 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. 17-GEMMASCOPE-RES-16K
    11. 10294
    Prev
    Next
    INDEX
    Explanations

    ethical and procedural language pertaining to legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     således
    -0.73
     poichè
    -0.69
     yalnızca
    -0.68
    几人
    -0.66
     endast
    -0.66
    共に
    -0.66
     الرياضيه
    -0.65
    скоре
    -0.65
     serupa
    -0.64
    已是
    -0.63
    POSITIVE LOGITS
     really
    1.13
     [
    1.06
     basically
    1.01
     somebody
    1.00
     kind
    0.95
     stuff
    0.92
     everybody
    0.92
     sort
    0.88
     veldig
    0.88
    basically
    0.87
    Activations Density 1.333%

    No Known Activations