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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2034
    Prev
    Next
    INDEX
    Explanations

    mentions of the artist Iggy Azalea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    musician names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Italijanski
    -0.62
    RegressionTest
    -0.59
    writeFieldEnd
    -0.57
    ंदीखरीदारी
    -0.55
    EDEFAULT
    -0.54
    setopt
    -0.54
     IBOutlet
    -0.53
    fromnode
    -0.52
     vtk
    -0.52
     Infórmanos
    -0.52
    POSITIVE LOGITS
     Weeknd
    0.75
     Minaj
    0.63
     Drake
    0.55
     Instagram
    0.55
     Sheeran
    0.54
     Rihanna
    0.52
     Snapchat
    0.50
    Drake
    0.50
    riezmann
    0.49
    Rihanna
    0.47
    Activations Density 0.011%

    No Known Activations