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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 8402
    Prev
    Next
    INDEX
    Explanations

    references to California and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     הופ
    -0.62
     Starling
    -0.61
     Uruguay
    -0.59
     Urugu
    -0.59
     Tirana
    -0.56
     Ugandan
    -0.55
    didSet
    -0.54
     Abdulla
    -0.54
     Wyn
    -0.54
    Uruguay
    -0.53
    POSITIVE LOGITS
     California
    2.90
    California
    2.76
     CALIFORNIA
    2.50
     Calif
    2.43
     california
    2.35
     Californian
    2.31
    CALIFORNIA
    2.30
     Califor
    2.28
    california
    2.13
    Calif
    2.13
    Activations Density 0.092%

    No Known Activations