© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7794
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     located
    -0.69
     Located
    -0.57
    located
    -0.52
     location
    -0.50
    Located
    -0.50
     situé
    -0.49
     locations
    -0.48
     LOCATION
    -0.45
     LOCATIONS
    -0.43
     locate
    -0.41
    POSITIVE LOGITS
     oprot
    0.73
     EconPapers
    0.68
    TabIndex
    0.62
    MemoryWarning
    0.51
    rungsseite
    0.50
     Bioaccumulative
    0.48
     utafiti
    0.47
    RenderAtEndOf
    0.46
    complexContent
    0.45
    Sklici
    0.45
    Activations Density 0.138%

    No Known Activations