Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 11716
    Prev
    Next
    INDEX
    Explanations

    options for selection or choice within a variety of categories, such as products or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.94
    principalTable
    -0.83
    BufferException
    -0.79
    下载附件
    -0.71
    MLLoader
    -0.70
     вікі
    -0.69
    quartered
    -0.69
    LookAnd
    -0.67
     Paglinawan
    -0.66
    featureID
    -0.65
    POSITIVE LOGITS
     choose
    1.01
     Choose
    0.90
     choices
    0.88
    choose
    0.88
     options
    0.86
    Choose
    0.85
     choice
    0.83
     elegir
    0.79
     select
    0.78
     selection
    0.76
    Activations Density 0.104%

    No Known Activations