© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5387
    Prev
    Next
    INDEX
    Explanations

    geographic locations or place names

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

    US States, Canadian provinces, or regions

    np_acts-logits-general · gemini-2.0-flash

    states and provinces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.50
     múl
    -0.48
     समीक्षाएं
    -0.46
    咖
    -0.45
    ério
    -0.43
    之一
    -0.42
    kheim
    -0.40
     sfor
    -0.40
    CppCodeGen
    -0.40
    MULTI
    -0.40
    POSITIVE LOGITS
     statewide
    1.05
     State
    1.02
     setState
    0.98
     province
    0.94
     state
    0.93
     Province
    0.93
     Governor
    0.86
     Majefty
    0.86
    state
    0.86
     getState
    0.84
    Activations Density 0.392%

    No Known Activations