© 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. 15-GEMMASCOPE-RES-16K
    11. 2065
    Prev
    Next
    INDEX
    Explanations

    descriptions and characteristics of physical structures or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.53
    setPadding
    -0.37
     cube
    -0.35
    psychology
    -0.34
    Bos
    -0.33
     cubos
    -0.33
     Bos
    -0.32
    Square
    -0.32
     dollar
    -0.32
    cube
    -0.32
    POSITIVE LOGITS
     BorderSide
    0.90
     length
    0.75
     panjang
    0.73
     Panjang
    0.71
    这条
    0.68
     linear
    0.68
     strip
    0.67
     lengths
    0.67
     lijn
    0.66
     linearity
    0.66
    Activations Density 1.800%

    No Known Activations