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. 21-GEMMASCOPE-RES-16K
    6. 3058
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mengen
    -0.50
    ]));
    
    -0.48
    }{*}{
    -0.48
    |}{}
    -0.47
    stech
    -0.47
    welche
    -0.47
     AssemblyCompany
    -0.46
    chige
    -0.46
     كمان
    -0.46
    ailleurs
    -0.45
    POSITIVE LOGITS
    HAPPY
    0.95
    webElementXpaths
    0.89
     happy
    0.89
     HAPPY
    0.86
    happy
    0.84
     camper
    0.83
     Happy
    0.81
     campers
    0.79
    Happy
    0.78
     feliz
    0.77
    Activations Density 0.038%

    No Known Activations