© 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. 15940
    Prev
    Next
    INDEX
    Explanations

    measurements related to length and height

    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
     crossroads
    -0.50
     cog
    -0.49
    گردان
    -0.48
     Crossroads
    -0.48
     dots
    -0.48
    stagland
    -0.47
    inde
    -0.47
    clas
    -0.46
    yeth
    -0.45
     Kershaw
    -0.44
    POSITIVE LOGITS
     meters
    0.88
     metre
    0.87
     Meter
    0.85
     metres
    0.84
     meter
    0.83
     Meters
    0.81
     height
    0.77
     METER
    0.77
    AndEndTag
    0.75
    AnchorStyles
    0.75
    Activations Density 0.119%

    No Known Activations