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. 20-GEMMASCOPE-RES-16K
    6. 10972
    Prev
    Next
    INDEX
    Explanations

    instances of social activities and interactions related to going out

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "out," "night," or "evening."

    np_acts-logits-general · gemini-2.0-flash

    social events and dining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.71
    PropertyGroup
    -0.62
    GEBURTSDATUM
    -0.55
    ">//
    -0.55
    AnimationsModule
    -0.51
    Hozzáférés
    -0.51
     >=",
    -0.48
    })));
    -0.47
    WithIOException
    -0.46
    feder
    -0.45
    POSITIVE LOGITS
     outing
    1.16
     outings
    1.15
     out
    0.97
     Out
    0.88
    外出
    0.86
     socializing
    0.83
    Out
    0.82
     sortie
    0.81
     errands
    0.80
     restaurants
    0.80
    Activations Density 0.174%

    No Known Activations