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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6774
    Prev
    Next
    INDEX
    Explanations

    references to graphical elements or boxes in a layout context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }`).
    -0.77
     pleaſure
    -0.77
    */),
    -0.76
    EndInit
    -0.76
     bershka
    -0.74
    ']):
    -0.72
     Lur
    -0.72
    DSA
    -0.68
     cardiaque
    -0.68
    ]]:
    -0.68
    POSITIVE LOGITS
    box
    3.97
     box
    3.93
     Box
    3.85
    Box
    3.74
    BOX
    3.57
     BOX
    3.52
     boxes
    3.28
    boxes
    3.19
     Boxes
    3.05
    Boxes
    2.69
    Activations Density 0.042%

    No Known Activations