Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 12781
    Prev
    Next
    INDEX
    Explanations

    mentions of social media platforms and user engagement on those platforms

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

    social media platforms

    np_acts-logits-general · gemini-2.0-flash

    social media and online services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.78
    addCriterion
    -0.70
    RegressionTest
    -0.66
    ConstraintMaker
    -0.66
    gdx
    -0.62
     Facebook
    -0.62
    ParallelGroup
    -0.61
     Instagram
    -0.61
    autoreleasepool
    -0.61
    FXML
    -0.61
    POSITIVE LOGITS
     feed
    0.66
     account
    0.64
    ®
    0.58
     page
    0.57
     kautta
    0.57
     handle
    0.56
    Personensuche
    0.54
     üzerinden
    0.53
    ®,
    0.53
     géant
    0.52
    Activations Density 0.160%

    No Known Activations