© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35670
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "panda" in various forms and contexts

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

    Panda or pandas

    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
     CreateTagHelper
    -0.44
    igslist
    -0.43
    bufio
    -0.42
    neté
    -0.40
    ⓧ
    -0.39
    OGND
    -0.38
     وتسجيلات
    -0.38
    詹
    -0.36
    JKLM
    -0.36
     ujednoznacz
    -0.36
    POSITIVE LOGITS
     Panda
    2.33
    Panda
    2.13
     panda
    2.03
    panda
    1.80
     Pandas
    1.32
    熊猫
    1.27
    🐼
    1.18
     pandas
    1.05
    pandas
    0.96
    Pand
    0.81
    Activations Density 0.002%

    No Known Activations