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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15334
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming

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

    Code, acronyms, and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    CU_ or CPL_

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     D
    -0.63
     B
    -0.53
     S
    -0.50
     li
    -0.47
     Ho
    -0.45
     W
    -0.45
     E
    -0.44
     d
    -0.44
     K
    -0.43
     mu
    -0.43
    POSITIVE LOGITS
     Efq
    1.34
     Monfieur
    1.33
     myſelf
    1.27
     itſelf
    1.24
     Мексичка
    1.23
     Jefus
    1.21
    ſelf
    1.19
     whoſe
    1.16
     himſelf
    1.15
     leaſt
    1.12
    Activations Density 0.310%

    No Known Activations