© 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. 7-GEMMASCOPE-RES-16K
    6. 3265
    Prev
    Next
    INDEX
    Explanations

    significant procedural or legal terms related to specific evidence or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     termica
    -0.53
     individuale
    -0.52
     insegna
    -0.52
    DockStyle
    -0.51
     tecnici
    -0.50
     impegno
    -0.50
     läh
    -0.48
     buoni
    -0.48
     ciasc
    -0.47
     asemenea
    -0.47
    POSITIVE LOGITS
    #![
    0.63
    Sklici
    0.62
    новниш
    0.60
    editorial
    0.59
    weeper
    0.59
    coroutines
    0.59
    ც
    0.58
    "){
    
    0.58
    chinen
    0.58
    ValueStyle
    0.58
    Activations Density 0.177%

    No Known Activations