Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5827
    Prev
    Next
    INDEX
    Explanations

    references to inventions or devices in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.54
    mobileqq
    -0.52
    contentLoaded
    -0.51
    :][
    -0.50
    SBATCH
    -0.50
     oprot
    -0.49
    WithMany
    -0.48
     Paglinawan
    -0.47
    cshtml
    -0.47
     otomatig
    -0.47
    POSITIVE LOGITS
     technique
    0.94
    technique
    0.78
     invention
    0.76
     Technique
    0.76
     phenomena
    0.75
     TECHNIQUE
    0.72
     phenomenon
    0.72
    Technique
    0.71
    invention
    0.66
     techniques
    0.61
    Activations Density 0.129%

    No Known Activations