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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 2398
    Prev
    Next
    INDEX
    Explanations

    instances of the word "scattered" and words related to assistance or help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.45
     gereken
    -0.43
    :✨
    -0.42
     AssemblyCompany
    -0.42
     dentistry
    -0.41
    énario
    -0.40
     Recession
    -0.40
    Datuak
    -0.40
    دانشنامهٔ
    -0.39
     TV
    -0.37
    POSITIVE LOGITS
     scattering
    0.94
    Scatter
    0.94
     scattered
    0.90
    scatter
    0.89
     scatter
    0.88
     Scatter
    0.85
     dispersion
    0.85
     dispersed
    0.81
     Scattering
    0.78
     scat
    0.73
    Activations Density 0.199%

    No Known Activations