© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11446
    Prev
    Next
    INDEX
    Explanations

    methods and techniques related to scientific research and measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     aank
    -0.49
     perdida
    -0.47
     dob
    -0.47
    حياته
    -0.45
     roli
    -0.43
     situada
    -0.42
     comiendo
    -0.42
    Nikki
    -0.42
     "'";
    -0.40
     dön
    -0.40
    POSITIVE LOGITS
    tagHelperRunner
    0.97
    StoryboardSegue
    0.93
    gorithm
    0.79
     technique
    0.78
     actionMode
    0.77
     techniques
    0.76
     methodology
    0.74
     onOptions
    0.74
    cedures
    0.73
     methodologies
    0.73
    Activations Density 1.059%

    No Known Activations