Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8955
    Prev
    Next
    INDEX
    Explanations

    the use of the word "However" in various contexts

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

    but however

    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
     BoxFit
    -0.59
     متعلقه
    -0.40
     BorderRadius
    -0.39
     tomada
    -0.39
    ContentView
    -0.39
    麦
    -0.39
     zove
    -0.38
    cestry
    -0.36
    batim
    -0.36
    ringa
    -0.36
    POSITIVE LOGITS
     But
    1.03
    But
    1.01
     but
    0.86
    but
    0.82
    しかし
    0.81
     However
    0.81
     BUT
    0.81
    BUT
    0.79
    However
    0.79
     nhưng
    0.71
    Activations Density 0.034%

    No Known Activations