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. 6262
    Prev
    Next
    INDEX
    Explanations

    the word "whereas" in different forms and contexts

    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
    k
    -0.78
     must
    -0.75
     "
    -0.72
    n
    -0.69
    ch
    -0.67
     Stein
    -0.66
    н
    -0.66
     home
    -0.66
     Dorn
    -0.66
    in
    -0.64
    POSITIVE LOGITS
    whereas
    2.58
     whereas
    2.51
    Whereas
    2.51
     Whereas
    2.49
     WHEREAS
    1.51
     sedangkan
    1.35
    DockStyle
    1.34
    WHEREAS
    1.28
     whilst
    1.23
     Whilst
    1.15
    Activations Density 0.080%

    No Known Activations