© 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. 11209
    Prev
    Next
    INDEX
    Explanations

    specific patterns and keywords related to tags and categorization

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

    Two-letter abbreviations

    np_acts-logits-general · gemini-2.0-flash

    eg to gene or egocentric

    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
    StoryboardSegue
    -0.71
    esModule
    -0.67
     ویکی‌پدی
    -0.66
     disambiguazione
    -0.64
    :✨
    -0.63
     useStyles
    -0.62
     Catawiki
    -0.62
    >*/
    -0.61
     imageNamed
    -0.60
    Diwedd
    -0.59
    POSITIVE LOGITS
    ging
    1.08
    gy
    0.95
    ged
    0.92
    ggg
    0.89
    gs
    0.87
    ger
    0.84
    gers
    0.84
    gin
    0.81
    gggg
    0.80
    GER
    0.79
    Activations Density 0.921%

    No Known Activations