© 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. 3-GEMMASCOPE-RES-16K
    11. 8122
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and areas

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

    references to a geographic locality or surrounding region.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
     mergeFrom
    -0.55
    GEBURTSDATUM
    -0.55
    Pranala
    -0.54
    orges
    -0.48
    glBindBuffer
    -0.44
    ुल
    -0.43
    院長
    -0.42
     AssemblyProduct
    -0.42
    őtt
    -0.42
     चुनें
    -0.41
    POSITIVE LOGITS
     area
    1.64
     region
    1.22
    area
    1.21
     AREA
    1.14
     Area
    1.13
     Gegend
    1.11
     området
    1.07
     neighborhood
    1.02
    Area
    1.02
     vicinity
    1.01
    Activations Density 0.088%

    No Known Activations