© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56218
    Prev
    Next
    INDEX
    Explanations

    terms related to showcasing or presenting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    il
    -0.69
    p
    -0.66
    ine
    -0.66
    ina
    -0.65
    um
    -0.64
    lib
    -0.63
    td
    -0.62
    op
    -0.61
     sleep
    -0.60
     strana
    -0.60
    POSITIVE LOGITS
     showcase
    1.70
     showcases
    1.65
     Showcase
    1.64
    Showcase
    1.56
    showcase
    1.55
     showcasing
    1.47
     showcased
    1.40
    casing
    1.09
     fhew
    1.07
     themſelves
    1.05
    Activations Density 0.004%

    No Known Activations