© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101154
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, particularly related to the Pacific region and time zones

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

    Pacific time zones and western states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scher
    -0.40
     UK
    -0.38
    سط
    -0.38
     ECB
    -0.38
     Johan
    -0.37
    nokia
    -0.37
    TypedDataSet
    -0.36
    汝
    -0.35
     IFA
    -0.35
    瘤
    -0.35
    POSITIVE LOGITS
     California
    1.03
     Kalifor
    0.98
    California
    0.98
     Californian
    0.92
     CALIFORNIA
    0.88
     Califor
    0.87
     Californie
    0.85
     Oregon
    0.84
    Oregon
    0.81
     california
    0.80
    Activations Density 0.048%

    No Known Activations