© 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. 6510
    Prev
    Next
    INDEX
    Explanations

    disclaimers and disclaiming information regarding medical advice and services

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

    Statements of disclaimer or lack of guarantee

    np_acts-logits-general · gemini-2.0-flash

    disclaimers and accuracy statements

    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
    TemporalType
    -0.58
     CreateTagHelper
    -0.56
    tedy
    -0.53
     then
    -0.50
    ніципалі
    -0.49
     lets
    -0.48
     simplest
    -0.48
     façons
    -0.47
    trud
    -0.46
     bad
    -0.46
    POSITIVE LOGITS
     disclaimer
    0.76
     subject
    0.75
     accuracy
    0.72
    subject
    0.70
     Disclaimer
    0.67
    あくまで
    0.64
    Disclaimer
    0.62
    Statements
    0.62
    Subject
    0.62
    opinions
    0.61
    Activations Density 0.344%

    No Known Activations