© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2916
    Prev
    Next
    INDEX
    Explanations

    HTML class attributes in the document

    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
    Geplaatst
    -0.90
     referenties
    -0.84
    StructEnd
    -0.77
    تقاوى
    -0.76
     nakalista
    -0.75
    IVEREF
    -0.74
    setVerticalGroup
    -0.73
     <<<<<<<<<<<<<<
    -0.72
     estekak
    -0.72
    Hochspringen
    -0.71
    POSITIVE LOGITS
    KNOWN
    0.55
    ImageContext
    0.54
     div
    0.54
     G
    0.53
     ward
    0.52
    трим
    0.52
     old
    0.52
     led
    0.50
    Into
    0.49
    weile
    0.49
    Activations Density 0.029%

    No Known Activations