© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 12611
    Prev
    Next
    INDEX
    Explanations

    different forms of the word "pal" or related terms involving palmitate, phosphatides, and related concepts in various contexts

    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
    delwed
    -0.42
    otle
    -0.41
     Gel
    -0.37
     Exchange
    -0.36
     Tower
    -0.36
    cheiben
    -0.36
    tikz
    -0.35
    Ob
    -0.35
     depositphotos
    -0.35
     Ve
    -0.35
    POSITIVE LOGITS
     pal
    0.64
    BufferException
    0.63
    pal
    0.62
    MemoryWarning
    0.62
     BoxDecoration
    0.61
    StoreMessageInfo
    0.60
     BoxFit
    0.57
    ArrowToggle
    0.57
     вікісторінку
    0.55
     Palmer
    0.54
    Activations Density 1.856%

    No Known Activations