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. 1-GEMMASCOPE-RES-16K
    6. 9726
    Prev
    Next
    INDEX
    Explanations

    terms related to engagement and involvement in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.67
    NamedQueries
    -0.65
    InvalidProtocol
    -0.64
     ThemeData
    -0.63
     AttributeSet
    -0.63
    ftagPool
    -0.61
     FormData
    -0.61
    bitField
    -0.60
    ukone
    -0.60
    SharedDtor
    -0.59
    POSITIVE LOGITS
     engaging
    2.32
     engage
    2.31
     Engaging
    2.19
     engages
    2.11
    engage
    2.02
     Engage
    1.99
     engagement
    1.99
    Engage
    1.95
    eng
    1.75
    Eng
    1.73
    Activations Density 0.072%

    No Known Activations