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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3667
    Prev
    Next
    INDEX
    Explanations

    references to firearms and associated equipment specifications

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

    Appears before mathematical symbols or code-related words

    np_acts-logits-general · gemini-2.0-flash

    magazine

    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
     المعيارى
    -0.85
     Cabin
    -0.60
     leprosy
    -0.55
     cabins
    -0.55
     cabin
    -0.53
     Réponses
    -0.52
     caravans
    -0.51
     impea
    -0.50
     lasso
    -0.50
     Merv
    -0.50
    POSITIVE LOGITS
     magazines
    0.83
     magazine
    0.78
     mag
    0.71
     mags
    0.70
     polymer
    0.70
     Magazine
    0.67
    DotNetBar
    0.67
    StoryboardSegue
    0.67
    magazine
    0.65
     Mag
    0.64
    Activations Density 0.053%

    No Known Activations