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. 2145
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" and variations of its usage in different contexts

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

    that followed by a word

    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
    RenderAtEndOf
    -0.39
     manner
    -0.34
     tombs
    -0.33
    Weitere
    -0.32
    tinya
    -0.32
     outline
    -0.32
     tower
    -0.31
     nuovamente
    -0.31
    ProgressHUD
    -0.31
     torn
    -0.31
    POSITIVE LOGITS
     WaitForSeconds
    0.59
    TProtocol
    0.54
    AddTagHelper
    0.53
     StatefulWidget
    0.52
    ->___
    0.51
     przecież
    0.51
    Билгалдахарш
    0.51
    GEBURTSDATUM
    0.51
     ActionListener
    0.51
    Life
    0.51
    Activations Density 0.030%

    No Known Activations