© 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. 18-GEMMASCOPE-RES-16K
    11. 10019
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and testing

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

    preceding a noun

    np_acts-logits-general · gemini-2.0-flash

    specific noun followed by a concept

    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
    ագրություններ
    -1.02
    rungsseite
    -0.81
     snippetHide
    -0.77
    Tembelea
    -0.75
    SharedDtor
    -0.74
     pinulongan
    -0.70
    ngdoc
    -0.69
     consultato
    -0.67
     Wicidata
    -0.66
    脚注の使い方
    -0.66
    POSITIVE LOGITS
     comod
    0.46
    drawImage
    0.43
    ന്ന
    0.43
    /
    0.41
     paradigm
    0.41
    putra
    0.41
     option
    0.40
     category
    0.39
     modelAndView
    0.39
    合わせ
    0.39
    Activations Density 0.579%

    No Known Activations