© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 14674
    Prev
    Next
    INDEX
    Explanations

    mentions of countries involved in a conflict or security situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scandinavia
    -0.81
     Deutschland
    -0.78
     Europe
    -0.73
    España
    -0.71
     España
    -0.70
    Spain
    -0.70
    Europe
    -0.69
     europe
    -0.67
     France
    -0.67
     Australians
    -0.67
    POSITIVE LOGITS
     Chad
    0.62
    ̍t
    0.55
     Democratic
    0.54
     Kyr
    0.54
    ஈ
    0.53
     Sierra
    0.52
     Burk
    0.51
     utafitiHapana
    0.51
    кипедия
    0.51
     timedelta
    0.50
    Activations Density 0.236%

    No Known Activations