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. 11041
    Prev
    Next
    INDEX
    Explanations

    instances or references to geographical or thematic dispersion

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

    "Across" followed by a preposition/location

    np_acts-logits-general · gemini-2.0-flash

    across regions and categories

    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
     @"/
    -0.83
    hasMoreElements
    -0.82
    ResponseEntity
    -0.76
    цездатний
    -0.72
    gameserver
    -0.68
    ukone
    -0.68
     članak
    -0.68
     vermelhas
    -0.67
     engraçadas
    -0.66
    HasAnnotation
    -0.65
    POSITIVE LOGITS
     continents
    0.82
     generations
    0.80
     borders
    0.74
     hinweg
    0.70
     genres
    0.69
     multiple
    0.68
     Europe
    0.67
     genders
    0.67
     disciplines
    0.66
     spectrum
    0.66
    Activations Density 0.091%

    No Known Activations