© 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. 20-GEMMASCOPE-RES-16K
    11. 8863
    Prev
    Next
    INDEX
    Explanations

    references to the term "Ram" in various contexts

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

    Ram followed by various suffixes

    np_acts-logits-general · gemini-2.0-flash

    Ram and subsequent syllables

    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
     Wikimedijinoj
    -0.90
     InputDecoration
    -0.88
    LEncoder
    -0.82
    RenderAtEndOf
    -0.82
    帖最后由
    -0.81
    ChildScrollView
    -0.80
    amins
    -0.79
    bewerken
    -0.78
    ImageContext
    -0.77
    openConnection
    -0.77
    POSITIVE LOGITS
     Ram
    0.79
    Ram
    0.68
     ram
    0.68
    ram
    0.67
     rams
    0.64
     Rams
    0.63
    Rams
    0.56
    lamb
    0.56
     lamb
    0.51
    paging
    0.47
    Activations Density 0.092%

    No Known Activations