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. 18-GEMMASCOPE-RES-16K
    6. 10573
    Prev
    Next
    INDEX
    Explanations

    elements related to positive social interactions and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     megsz
    -0.45
    ">//
    -0.45
     rowspan
    -0.44
     banheiro
    -0.43
     daglig
    -0.42
    ائ
    -0.41
    zijde
    -0.41
    getLogger
    -0.41
    Daily
    -0.41
    uali
    -0.40
    POSITIVE LOGITS
     outing
    1.09
     errands
    1.01
     outings
    0.98
     errand
    0.88
     meetup
    0.85
     shopping
    0.84
     Meetup
    0.78
     excursion
    0.78
     sightseeing
    0.76
     trips
    0.76
    Activations Density 0.230%

    No Known Activations