© 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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5350
    Prev
    Next
    INDEX
    Explanations

    terms related to engineering and physical sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.64
     RouterModule
    -0.60
     gagné
    -0.58
    yafet
    -0.55
     AssemblyCulture
    -0.55
     gră
    -0.54
     VAT
    -0.53
     المعيارى
    -0.53
     épic
    -0.52
     gear
    -0.52
    POSITIVE LOGITS
     engineering
    1.15
     Engineering
    1.11
    Engineering
    1.07
     upload
    1.05
     ENGINEERING
    1.02
    engineering
    0.99
     uploading
    0.99
    ENGINEERING
    0.96
     uploads
    0.94
    Sciences
    0.88
    Activations Density 0.070%

    No Known Activations