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

    Neuronpedia

    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 30647
    Prev
    Next
    INDEX
    Explanations

    specific anatomical terms or structures related to the human body

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

    pituitary gland

    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
    McC
    -0.39
     przed
    -0.39
    Predecesor
    -0.39
    xbb
    -0.38
     pép
    -0.37
    AsUp
    -0.37
     Uso
    -0.37
     directo
    -0.37
     Rede
    -0.37
     béné
    -0.37
    POSITIVE LOGITS
     cauliflower
    2.08
     Cauliflower
    1.94
    liflower
    1.78
    ituitary
    0.65
    cloudflare
    0.60
     Tofu
    0.59
    IndentedString
    0.58
    cloudf
    0.58
     Clou
    0.57
     autorytatywna
    0.56
    Activations Density 0.000%

    No Known Activations