Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 13949
    Prev
    Next
    INDEX
    Explanations

    features related to multifocal eyeglasses and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RequestMethod
    -0.49
    LEVANT
    -0.48
    oprecipitation
    -0.47
    ParallelGroup
    -0.46
    PerformLayout
    -0.45
    CodedInputStream
    -0.44
    VersionUID
    -0.44
     MainAxisSize
    -0.43
    WebServlet
    -0.43
     loamy
    -0.43
    POSITIVE LOGITS
     glasses
    1.77
     lenses
    1.61
     Glasses
    1.58
     lens
    1.52
     eyewear
    1.51
     eyeglasses
    1.50
    glasses
    1.47
     spectacles
    1.44
     Lens
    1.43
     Eye
    1.40
    Activations Density 0.288%

    No Known Activations