© 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. 24-GEMMASCOPE-RES-16K
    11. 12601
    Prev
    Next
    INDEX
    Explanations

    references to cities and urban governance

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

    "City" followed by locations or institutions

    np_acts-logits-general · gemini-2.0-flash

    city hall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -0.71
     MediatR
    -0.65
     pinulongan
    -0.61
    Viited
    -0.58
    aspectj
    -0.58
     commandement
    -0.57
    itism
    -0.57
    ソッド
    -0.57
    المكان
    -0.57
    GEBURTSDATUM
    -0.56
    POSITIVE LOGITS
     hall
    0.90
    wide
    0.84
     Hall
    0.81
     council
    0.80
     limits
    0.79
     Limits
    0.76
    hall
    0.76
    scape
    0.74
    limits
    0.72
     centre
    0.70
    Activations Density 0.064%

    No Known Activations