© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4032
    Prev
    Next
    INDEX
    Explanations

    mentions of celebrities and their property details

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

    "Read More" links on website articles

    np_acts-logits-general · gemini-2.0-flash

    Read More

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resource
    -0.43
     tepung
    -0.39
     considerable
    -0.38
     RESOURCE
    -0.38
     substantial
    -0.37
     Resource
    -0.36
     esclavos
    -0.35
     资源
    -0.35
     Anſ
    -0.35
    문
    -0.35
    POSITIVE LOGITS
    dailymail
    0.60
    RegressionTest
    0.54
    Referanser
    0.53
    Jeografia
    0.52
    libft
    0.52
    ViewImports
    0.52
    enderror
    0.51
    IsContent
    0.50
     AssemblyProduct
    0.48
    Notae
    0.47
    Activations Density 0.092%

    No Known Activations