© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6661
    Prev
    Next
    INDEX
    Explanations

    the word "otherwise" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jagger
    -0.73
    ânsito
    -0.72
    cmath
    -0.71
     Haller
    -0.69
     Checkpoint
    -0.69
    chọn
    -0.68
     vectorielles
    -0.68
    ividual
    -0.68
    `{.
    -0.67
     aantal
    -0.66
    POSITIVE LOGITS
     Otherwise
    1.07
     OTHERWISE
    1.03
     otherwise
    1.02
    Otherwise
    1.01
    otherwise
    0.90
     Else
    0.88
    wise
    0.84
     else
    0.80
    不然
    0.79
    Else
    0.79
    Activations Density 0.088%

    No Known Activations