© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 67744
    Prev
    Next
    INDEX
    Explanations

    the word "either" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introduces an alternative or option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    crollView
    -0.44
    érité
    -0.39
     arşivlendi
    -0.39
     hashCode
    -0.38
    GHI
    -0.38
     MIL
    -0.37
    userdetails
    -0.36
    enscha
    -0.35
    Демографія
    -0.35
    mtable
    -0.35
    POSITIVE LOGITS
     either
    1.14
    either
    1.13
    Either
    1.10
     Either
    1.05
     entweder
    1.02
     либо
    0.79
    ITHER
    0.76
    weder
    0.73
    要么
    0.70
    elif
    0.67
    Activations Density 0.017%

    No Known Activations