Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6575
    Prev
    Next
    INDEX
    Explanations

    terms related to regional or geographical context

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

    "Regional" followed by different words

    np_acts-logits-general · gemini-2.0-flash

    regional qualifiers

    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
     InputDecoration
    -0.95
    uxxxx
    -0.74
    công
    -0.70
    ETHING
    -0.70
     Morde
    -0.69
     Samb
    -0.68
     TTS
    -0.65
     Taras
    -0.65
    Personensuche
    -0.65
     referenties
    -0.63
    POSITIVE LOGITS
    region
    1.02
     REGION
    0.99
     Region
    0.98
     regions
    0.97
     region
    0.96
    REGION
    0.94
    regions
    0.94
    Regions
    0.90
    Region
    0.85
     regiones
    0.84
    Activations Density 0.138%

    No Known Activations