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. 3-GEMMASCOPE-RES-16K
    6. 16097
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and their various conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     are
    -0.83
     were
    -0.74
     WERE
    -0.57
    들은
    -0.52
    ignez
    -0.52
    were
    -0.51
    def
    -0.51
    Datuak
    -0.51
     have
    -0.49
     Were
    -0.49
    POSITIVE LOGITS
     CreateTagHelper
    0.86
     ProtoMessage
    0.78
    saraba
    0.76
     незавершена
    0.75
     itſelf
    0.72
     Monfieur
    0.67
     للمعارف
    0.66
    astify
    0.65
     himſelf
    0.65
     المعيارى
    0.63
    Activations Density 0.314%

    No Known Activations