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. 24472
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "the."

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

    both ... and

    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
     etc
    -0.38
    ye
    -0.37
     YE
    -0.37
    crollView
    -0.36
    inac
    -0.35
     الع
    -0.34
    خه
    -0.33
    etc
    -0.33
     אח
    -0.33
     maybe
    -0.33
    POSITIVE LOGITS
    owohl
    1.11
    Both
    0.88
    Tanto
    0.88
     sowohl
    0.84
     Both
    0.81
     Tanto
    0.80
     both
    0.80
    both
    0.78
     BOTH
    0.77
     både
    0.74
    Activations Density 0.026%

    No Known Activations