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. 124866
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or separators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    뀔
    -0.43
    Helvetica
    -0.40
    Buenos
    -0.39
     even
    -0.39
     EnglishChoose
    -0.38
    Sama
    -0.38
    Files
    -0.37
    files
    -0.36
    Uploaded
    -0.36
    ism
    -0.35
    POSITIVE LOGITS
    LookAnd
    0.54
    Personendaten
    0.51
    يكب
    0.50
    انيف
    0.50
     Seeder
    0.49
    IVEREF
    0.49
     mourut
    0.48
     సౌకర్య
    0.47
     ujednoznacz
    0.46
     المعيارى
    0.46
    Activations Density 0.000%

    No Known Activations