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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 4560
    Prev
    Next
    INDEX
    Explanations

    references to social connections and making new friends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrNil
    -0.62
     <<<<<<<<<<<<<<
    -0.60
    helm
    -0.59
     FileInputStream
    -0.57
    يديا
    -0.56
    RenderAtEndOf
    -0.56
    WebElementEntity
    -0.56
    WebServlet
    -0.55
    ImageContext
    -0.54
    webElement
    -0.53
    POSITIVE LOGITS
     contacts
    0.94
     networking
    0.92
     Kontakte
    0.92
     connections
    0.88
     friendships
    0.87
     acquaintances
    0.83
     acquaintance
    0.82
     contactos
    0.77
     Networking
    0.74
    contacts
    0.74
    Activations Density 0.216%

    No Known Activations