© 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. 14-GEMMASCOPE-RES-16K
    11. 9053
    Prev
    Next
    INDEX
    Explanations

    technical terms related to surgical or medical procedures involving the removal or manipulation of tissues and implants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Filler
    -0.46
     
    -0.45
    besch
    -0.40
     Q
    -0.39
    补
    -0.39
    وصف
    -0.36
     (
    -0.36
     gefü
    -0.36
    zać
    -0.35
     scheme
    -0.34
    POSITIVE LOGITS
    rawDesc
    0.94
     removal
    0.86
    ThroughAttribute
    0.83
     Removal
    0.82
     StringTokenizer
    0.82
    SharedDtor
    0.81
    AndEndTag
    0.80
    RectangleBorder
    0.79
     Removing
    0.79
     متعلقه
    0.78
    Activations Density 0.392%

    No Known Activations