© 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. 5-GEMMASCOPE-RES-16K
    11. 10774
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and historical markers, particularly in Wales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portály
    -0.74
    AsUp
    -0.70
    migrationBuilder
    -0.70
    EnableWeb
    -0.67
    ClassNotFound
    -0.61
    Clik
    -0.59
    getSystemService
    -0.58
    ExtendWith
    -0.57
     CURIAM
    -0.54
    ніципа
    -0.50
    POSITIVE LOGITS
     Welsh
    1.18
    Welsh
    1.02
    Wales
    0.93
     Cymru
    0.91
     Wales
    0.88
     Cardiff
    0.78
     wales
    0.77
     Llan
    0.77
    Cardiff
    0.72
    wales
    0.71
    Activations Density 0.321%

    No Known Activations