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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3487
    Prev
    Next
    INDEX
    Explanations

    technical terms and details related to scientific research methodologies and aims

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    :✨
    -0.57
     Савезне
    -0.56
     שוליים
    -0.53
    ㎠
    -0.50
     kasarigan
    -0.49
     paraître
    -0.49
    Билгалдахарш
    -0.48
     lendemain
    -0.47
     pageContext
    -0.47
     headlines
    -0.47
    POSITIVE LOGITS
     plan
    0.42
     propose
    0.35
     цель
    0.35
     purpose
    0.34
     proposal
    0.34
     project
    0.34
     budget
    0.34
    
    0.33
     afin
    0.33
     budgeted
    0.32
    Activations Density 0.484%

    No Known Activations