© 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. 1590
    Prev
    Next
    INDEX
    Explanations

    queries involving knowledge or understanding, particularly in a legal context

    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
    ########.
    -0.55
     poveznice
    -0.48
    narr
    -0.48
    memberof
    -0.48
    comune
    -0.47
    ParallelGroup
    -0.47
    合衆
    -0.47
    sonian
    -0.47
    NARR
    -0.46
    RDONLY
    -0.45
    POSITIVE LOGITS
     expertise
    1.74
     expert
    1.72
     experts
    1.63
    expert
    1.50
     Expertise
    1.46
    Expert
    1.45
     Expert
    1.41
     EXPERT
    1.41
    expertise
    1.39
     Experts
    1.39
    Activations Density 0.328%

    No Known Activations