© 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. 2445
    Prev
    Next
    INDEX
    Explanations

    expressions of being impressed or admiration

    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
    PathVariable
    -0.63
     Holman
    -0.57
     Fielding
    -0.57
     gioia
    -0.55
    fficking
    -0.54
     contesto
    -0.52
    علان
    -0.51
    sellor
    -0.50
     Cal
    -0.49
     Normdatei
    -0.49
    POSITIVE LOGITS
     impressed
    2.63
     impress
    2.56
    Impressive
    1.98
     Impressive
    1.91
     impressive
    1.78
     impressions
    1.76
     impresion
    1.72
     impression
    1.71
     Impression
    1.69
    impres
    1.65
    Activations Density 0.043%

    No Known Activations