© 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. 9814
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values related to layout and styling

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

    CSS properties like width, size, and background

    np_acts-logits-general · gemini-2.0-flash

    style properties and dimensions

    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
    *>(
    -0.66
    InitVars
    -0.65
     “
    -0.65
    >");
    -0.64
    >",
    -0.64
     onBind
    -0.64
    '],$
    -0.64
    RegistryLite
    -0.64
     *>(
    -0.62
    <bos>
    -0.62
    POSITIVE LOGITS
     MainAxisSize
    0.65
    :
    0.57
     يتيمه
    0.52
     skydd
    0.51
    Addo
    0.50
    ChildScrollView
    0.50
     varandra
    0.48
    hassee
    0.46
    HasForeignKey
    0.46
    Zeneca
    0.45
    Activations Density 0.058%

    No Known Activations