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. 23-GEMMASCOPE-RES-16K
    6. 6257
    Prev
    Next
    INDEX
    Explanations

    specific types and features of eyeglasses or eyewear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.66
    CodedInputStream
    -0.62
    PerformLayout
    -0.58
    oprecipitation
    -0.57
    ChildScrollView
    -0.56
     RequestMethod
    -0.56
    UseVisualStyle
    -0.55
    ReusableCell
    -0.54
    WebServlet
    -0.54
    sizeCache
    -0.52
    POSITIVE LOGITS
     glasses
    1.65
     lenses
    1.56
     lens
    1.51
     Glasses
    1.44
     eyeglasses
    1.40
     Lens
    1.39
     eyewear
    1.39
    glasses
    1.38
     spectacles
    1.35
     Lenses
    1.30
    Activations Density 0.290%

    No Known Activations