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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 45473
    Prev
    Next
    INDEX
    Explanations

    concepts related to respectful and constructive interaction in communities

    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
     savings
    -0.39
    iastes
    -0.36
    estination
    -0.36
     ब्रेकडाउन
    -0.35
     المرجع
    -0.35
    الإنجليزية
    -0.34
    ității
    -0.33
    Tja
    -0.33
    transQ
    -0.33
     defect
    -0.32
    POSITIVE LOGITS
     jScrollPane
    0.60
    mobileqq
    0.54
     pinulongan
    0.53
     cherchés
    0.51
    fair
    0.51
    ContentAsync
    0.50
     referrerpolicy
    0.47
    NameInMap
    0.47
    twimg
    0.47
    astify
    0.47
    Activations Density 0.055%

    No Known Activations