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. 2-GEMMASCOPE-RES-16K
    6. 6171
    Prev
    Next
    INDEX
    Explanations

    references to specific countries and geopolitical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.86
     disambiguazione
    -0.78
    TypedDataSet
    -0.67
    
    -0.67
    ISupport
    -0.66
     nakalista
    -0.65
    providedIn
    -0.64
     Psal
    -0.64
    ьаж
    -0.64
    bootstrapcdn
    -0.62
    POSITIVE LOGITS
     overseas
    0.69
    FOREIGN
    0.68
     foreign
    0.64
    Overseas
    0.59
     Overseas
    0.59
     Abroad
    0.58
     Foreign
    0.58
     abroad
    0.57
     countries
    0.55
     FOREIGN
    0.55
    Activations Density 0.462%

    No Known Activations