Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7883
    Prev
    Next
    INDEX
    Explanations

    references to tax-related issues or challenges

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

    Follows words like "the" or "your"

    np_acts-logits-general · gemini-2.0-flash

    [adjective/determiner] [noun/gerund]

    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
     commissioners
    -0.77
     queen
    -0.74
     attorney
    -0.70
     academy
    -0.70
     commissioner
    -0.67
     kingdom
    -0.67
     hall
    -0.67
     republic
    -0.67
     pope
    -0.67
     pastor
    -0.66
    POSITIVE LOGITS
     varandra
    0.83
     Grecs
    0.83
     fumée
    0.81
     copertura
    0.81
     tiroirs
    0.81
     prisonniers
    0.81
     Case
    0.80
     spesa
    0.80
    väg
    0.80
     vägen
    0.79
    Activations Density 2.339%

    No Known Activations