© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14549
    Prev
    Next
    INDEX
    Explanations

    references to toys and their components or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     πως
    -0.88
    évaluateur
    -0.84
     grandkids
    -0.81
     Amongst
    -0.81
    MemoryWarning
    -0.80
    Autoritní
    -0.78
     oftentimes
    -0.78
     prepping
    -0.78
     somebody
    -0.77
    setVerticalGroup
    -0.77
    POSITIVE LOGITS
     XNUMX
    0.98
     ​​
    0.72
     analyzes
    0.65
    ſelves
    0.59
     ſy
    0.57
    ̵
    0.57
     ſtre
    0.51
     pleaſure
    0.50
     և
    0.50
    ​​
    0.50
    Activations Density 0.661%

    No Known Activations