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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 30245
    Prev
    Next
    INDEX
    Explanations

    phrases related to discovering items during treasure hunting or shopping

    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
     kontin
    -0.35
     étrangère
    -0.33
     theo
    -0.30
     agré
    -0.30
     vytvá
    -0.30
     assisti
    -0.30
     isti
    -0.30
     System
    -0.30
     Operation
    -0.29
    tlere
    -0.29
    POSITIVE LOGITS
     ब्रेकडाउन
    0.84
    expandindo
    0.81
     nakalista
    0.80
     يتيمه
    0.69
     noDo
    0.68
     المعيارى
    0.64
     Exactos
    0.59
    ronpa
    0.59
    Tembelea
    0.59
    хьтан
    0.58
    Activations Density 0.009%

    No Known Activations