© 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. 1-GEMMASCOPE-RES-16K
    6. 5810
    Prev
    Next
    INDEX
    Explanations

    references to poetry and poetic terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elkaar
    -0.80
    %]
    -0.77
     للاسماء
    -0.77
    ."]
    -0.76
     سكانية
    -0.75
     дописавши
    -0.74
     Réponses
    -0.72
    pexpr
    -0.71
     dekol
    -0.71
    soever
    -0.70
    POSITIVE LOGITS
    hl
    1.07
    HL
    0.86
    lines
    0.80
     verse
    0.64
    Хьажоргаш
    0.54
     Dal
    0.53
    PoolSize
    0.51
     cyber
    0.51
     Stuhl
    0.50
     wz
    0.50
    Activations Density 0.085%

    No Known Activations