© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1627
    Prev
    Next
    INDEX
    Explanations

    instances of descriptive adjectives and their relationships in a narrative context

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

    Adjective follows "A" or "a"

    np_acts-logits-general · gemini-2.0-flash

    "a" followed by a descriptive word

    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
     Roskov
    -0.91
    abestanden
    -0.76
    Sucesor
    -0.74
     StatelessWidget
    -0.66
     charité
    -0.65
    
    -0.64
     asas
    -0.62
     priorité
    -0.62
     &___
    -0.60
    AutoScale
    -0.60
    POSITIVE LOGITS
     pair
    0.79
     pile
    0.75
     piece
    0.74
     large
    0.70
     huge
    0.66
     faint
    0.65
     small
    0.64
     puddle
    0.63
     smile
    0.59
     gust
    0.59
    Activations Density 0.334%

    No Known Activations