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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-131K
    6. 113798
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical compounds or substances

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

    UG, ug, UGS, OUG, fenugreek

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pylori
    -0.43
    shadowOffset
    -0.40
    ={`${
    -0.38
    FontStyle
    -0.35
    ष्य
    -0.35
    oulli
    -0.34
    tableFuture
    -0.34
    ToTensor
    -0.34
     ICI
    -0.33
     kimia
    -0.32
    POSITIVE LOGITS
    UG
    2.39
    ug
    2.28
     UG
    1.84
     ug
    1.81
    ugs
    1.62
     Ug
    1.57
    ugg
    1.44
    Ug
    1.40
    ugi
    1.38
    uge
    1.30
    Activations Density 0.007%

    No Known Activations