© 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. 22-GEMMASCOPE-RES-16K
    11. 13342
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity of expert consultation and assistance in specialized fields

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

    Followed by "expert" or similar terms

    np_acts-logits-general · gemini-2.0-flash

    expert or specialist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.85
    SequentialGroup
    -0.80
     CURIAM
    -0.74
    applicant
    -0.69
    TagMode
    -0.66
     oprot
    -0.66
    нрави
    -0.63
    Билгалдахарш
    -0.63
     Recipients
    -0.62
     Donors
    -0.62
    POSITIVE LOGITS
     expert
    2.42
     experts
    2.39
    expert
    1.99
    experts
    1.93
     specialists
    1.90
     Expert
    1.88
    Expert
    1.87
     expertos
    1.85
     Experts
    1.82
     specialist
    1.81
    Activations Density 0.364%

    No Known Activations