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. 22-GEMMASCOPE-RES-16K
    6. 3398
    Prev
    Next
    INDEX
    Explanations

    topics related to citizenship laws and immigration policies

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

    Tokens related to being abroad or overseas

    np_acts-logits-general · gemini-2.0-flash

    abroad, overseas, foreign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.64
    setViewportView
    -0.53
    enterOuterAlt
    -0.53
    FontOfSize
    -0.50
    Filmografia
    -0.48
    ņas
    -0.46
     MonoBehaviour
    -0.45
    AnchorTagHelper
    -0.44
    deo
    -0.44
    AutoScaleMode
    -0.44
    POSITIVE LOGITS
     abroad
    2.37
     overseas
    2.35
     Abroad
    2.03
     foreign
    1.97
     foreigners
    1.94
     international
    1.94
     Overseas
    1.90
    Overseas
    1.86
     foreigner
    1.81
    international
    1.70
    Activations Density 0.895%

    No Known Activations