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. 4-GEMMASCOPE-RES-16K
    6. 11481
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.96
     Conſ
    -0.78
     Theſe
    -0.77
     Badger
    -0.76
     Stony
    -0.75
    Badger
    -0.75
     andes
    -0.74
     whoſe
    -0.72
     Dubuque
    -0.71
     RIPRODUZIONE
    -0.71
    POSITIVE LOGITS
     it
    2.03
     It
    1.68
     its
    1.56
    It
    1.55
    它
    1.51
    Its
    1.37
     Its
    1.35
     它
    1.35
    abestanden
    1.26
     IT
    1.23
    Activations Density 0.293%

    No Known Activations