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. 13147
    Prev
    Next
    INDEX
    Explanations

    negative forms of the verb "to be"

    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
     was
    -0.61
    fcntl
    -0.59
     Normdatei
    -0.57
    HasAnnotation
    -0.57
    SqlDataReader
    -0.55
    ItemGroup
    -0.55
    PropertyChanging
    -0.55
    was
    -0.54
    wasn
    -0.54
    awaiter
    -0.54
    POSITIVE LOGITS
     are
    2.04
    are
    1.90
     ARE
    1.89
     Are
    1.81
    Are
    1.78
     aren
    1.68
     são
    1.68
     were
    1.64
     sind
    1.64
     sont
    1.60
    Activations Density 0.412%

    No Known Activations