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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7475
    Prev
    Next
    INDEX
    Explanations

    metrics and issues related to memory and storage usage

    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
    wapV
    -0.37
    RoleId
    -0.35
    ImageIO
    -0.35
    sikan
    -0.35
     labios
    -0.34
    FromDate
    -0.31
    المصدر
    -0.31
    พล
    -0.31
     men
    -0.30
     introduce
    -0.30
    POSITIVE LOGITS
     disambiguazione
    0.65
    RegressionTest
    0.64
    RectangleBorder
    0.64
    verifyException
    0.63
    exitRule
    0.54
     Storage
    0.53
     BrowserModule
    0.53
     storage
    0.52
     kaarangay
    0.52
    MemoryWarning
    0.51
    Activations Density 0.029%

    No Known Activations