© 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. 8091
    Prev
    Next
    INDEX
    Explanations

    locations and descriptions related to travel and nature

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

    "British Columbia" or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    British Columbia and Vancouver

    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
     OTA
    -0.51
     Jeddah
    -0.51
     Akron
    -0.50
     tdci
    -0.50
    Ỡ
    -0.49
     hydroxy
    -0.49
     Nasser
    -0.48
     trì
    -0.48
     CommonModule
    -0.47
    ModelAdmin
    -0.47
    POSITIVE LOGITS
     BC
    0.85
     Vancouver
    0.78
    BC
    0.75
     Colombie
    0.73
     British
    0.69
    Vancouver
    0.69
     UBC
    0.66
    british
    0.66
     Okan
    0.65
    British
    0.64
    Activations Density 0.103%

    No Known Activations