© 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. 86000
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" used in various contexts to connect phrases or ideas

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

    and followed by words

    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
     ujednoznacz
    -0.61
    انيف
    -0.59
     itſelf
    -0.57
     Савезне
    -0.57
     royaltyfri
    -0.54
    piac
    -0.54
     getCustomer
    -0.51
    ValueStyle
    -0.51
     kapturem
    -0.50
     ſtate
    -0.50
    POSITIVE LOGITS
    And
    0.43
     argint
    0.40
     또
    0.39
    しかも
    0.39
     And
    0.39
    また
    0.37
    AndFlush
    0.37
     funny
    0.36
     fuckin
    0.35
    Außerdem
    0.35
    Activations Density 0.060%

    No Known Activations