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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15723
    Prev
    Next
    INDEX
    Explanations

    technical terminology and code related to programming structures

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

    Mathematical coordinates or points

    np_acts-logits-general · gemini-2.0-flash

    point or coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aronder
    -0.56
    getInputStream
    -0.53
    setWidth
    -0.49
    lineWidth
    -0.46
     competitive
    -0.46
     Aqueous
    -0.44
    chere
    -0.44
     shreds
    -0.43
    sheets
    -0.43
    sunter
    -0.43
    POSITIVE LOGITS
     coordinates
    1.14
     CGPoint
    1.04
     point
    0.98
     Coordinates
    0.96
     Point
    0.94
     points
    0.92
    CGPoint
    0.91
     coords
    0.89
    point
    0.86
     POINT
    0.86
    Activations Density 0.799%

    No Known Activations