© 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. 15256
    Prev
    Next
    INDEX
    Explanations

    terms related to computational methods and their applications in mathematics and engineering

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

    before volume numbers

    np_acts-logits-general · gemini-2.0-flash

    academic papers and technical terms

    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
    -
    -0.52
     “
    -0.49
    cor
    -0.48
     still
    -0.48
    core
    -0.47
     su
    -0.47
      
    -0.46
     si
    -0.45
     yet
    -0.45
     push
    -0.44
    POSITIVE LOGITS
     EconPapers
    1.05
     nakalista
    0.98
    ReusableCell
    0.93
    клопе
    0.92
    脚注の使い方
    0.91
    Geplaatst
    0.90
     Majefty
    0.90
    ."]
    0.89
    localctx
    0.89
     المعيارى
    0.88
    Activations Density 0.242%

    No Known Activations