© 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. 9941
    Prev
    Next
    INDEX
    Explanations

    expressions that highlight notable attributes or qualities of various subjects

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

    "... thing about ..." or "... part about ..."

    np_acts-logits-general · gemini-2.0-flash

    thing about

    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
     AppBundle
    -0.54
    errHandler
    -0.53
     pymongo
    -0.52
     restTemplate
    -0.50
    jsonwebtoken
    -0.50
    ANTLR
    -0.49
    __))
    -0.49
    Traceback
    -0.48
    XmlEnum
    -0.48
     ioutil
    -0.47
    POSITIVE LOGITS
     about
    1.11
     aspect
    0.92
    aspect
    0.81
    about
    0.79
     thing
    0.73
     feature
    0.73
    Aspect
    0.70
    About
    0.70
     taraf
    0.68
     ABOUT
    0.68
    Activations Density 0.120%

    No Known Activations