© 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. 20-GEMMASCOPE-RES-16K
    11. 7850
    Prev
    Next
    INDEX
    Explanations

    geographical locations and administrative divisions within Poland

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

    Polish place names

    np_acts-logits-general · gemini-2.0-flash

    Polish place names and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     gwaran
    -0.47
     is
    -0.43
     
    -0.42
     udział
    -0.42
     rozwój
    -0.42
     człowie
    -0.41
     sobą
    -0.41
     słoń
    -0.41
     przód
    -0.40
     v
    -0.40
    POSITIVE LOGITS
    LookAnd
    1.09
     ujednoznacz
    1.06
     Polish
    1.06
    __(/*!
    1.01
    Polish
    1.00
     Poland
    0.99
     يتيمه
    0.98
    PerformLayout
    0.98
     Kowalski
    0.97
    OGND
    0.97
    Activations Density 0.136%

    No Known Activations