© 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. 15-GEMMASCOPE-RES-16K
    11. 2970
    Prev
    Next
    INDEX
    Explanations

    references to specific numeric data or statistics

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

    complex scientific or technical terms and their definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    性が
    -0.44
    bor
    -0.44
    Показать
    -0.41
     kos
    -0.41
    fil
    -0.41
     ves
    -0.40
     =
    -0.40
    reden
    -0.40
    性を
    -0.40
     chào
    -0.40
    POSITIVE LOGITS
    httphttps
    0.96
    endphp
    0.91
    enderror
    0.88
     ostavi
    0.83
    principalColumn
    0.81
     EconPapers
    0.81
    thâu
    0.76
    تقاوى
    0.75
     arşivlendi
    0.74
     numberOfRows
    0.74
    Activations Density 0.194%

    No Known Activations