© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15254
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminology related to engineering and design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Stress, force, compression, and tensile concepts

    np_acts-logits-general · gemini-2.0-flash

    tensile and compression stress analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Przypisy
    -0.54
     sterling
    -0.54
    Autoritní
    -0.53
    EndInit
    -0.52
     aboard
    -0.51
    ActivityCompat
    -0.51
     bezel
    -0.51
     Biro
    -0.50
     scrambled
    -0.50
    PHYS
    -0.50
    POSITIVE LOGITS
    contentLoaded
    0.66
     beam
    0.60
     sezione
    0.59
     consultato
    0.58
     HttpNotFound
    0.57
    Loads
    0.56
    borderSide
    0.56
    polazione
    0.55
    tagHelperRunner
    0.55
     Load
    0.54
    Activations Density 0.271%

    No Known Activations