© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 13456
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to medical research and gene therapy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.86
     italienne
    -0.80
     financières
    -0.72
     originaux
    -0.70
     Polen
    -0.68
     fisica
    -0.68
    UserScript
    -0.68
    RegressionTest
    -0.68
    scalatest
    -0.67
    numerusform
    -0.67
    POSITIVE LOGITS
    ///</
    0.59
     '</
    0.59
    __*/
    0.58
    '],
    
    0.57
    ."</
    0.56
     }}(\
    0.56
    ()',
    0.56
    "]/
    0.56
    mnop
    0.55
    ERÍA
    0.55
    Activations Density 2.567%

    No Known Activations