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

    Neuronpedia

    APICircuit 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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36731
    Prev
    Next
    INDEX
    Explanations

    references to fortified structures or defenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.67
    MigrationBuilder
    -0.66
    ãng
    -0.63
     otomatig
    -0.60
     betweenstory
    -0.60
    rungsseite
    -0.59
     الاطلاع
    -0.58
    abetes
    -0.52
     beginnetje
    -0.52
    ztal
    -0.51
    POSITIVE LOGITS
     fortifications
    1.05
     fortification
    1.02
     fortress
    0.98
     fortific
    0.98
     Fortress
    0.93
     citadel
    0.86
     fortified
    0.83
     siege
    0.82
     guarding
    0.79
     nemico
    0.79
    Activations Density 0.045%

    No Known Activations