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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15847
    Prev
    Next
    INDEX
    Explanations

    terms related to music albums and media releases

    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
     effort
    -0.40
     efforts
    -0.39
    effort
    -0.39
     esfuerzo
    -0.37
    BagConstraints
    -0.36
    stretchr
    -0.34
    enfone
    -0.34
    ruptedException
    -0.34
     esfuerzos
    -0.34
    arnas
    -0.34
    POSITIVE LOGITS
     DVD
    0.77
     DVDs
    0.75
     album
    0.71
     albums
    0.70
     CDs
    0.69
    DVD
    0.68
     CD
    0.65
     dvd
    0.63
     discs
    0.63
    Autoritní
    0.60
    Activations Density 0.136%

    No Known Activations