© 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. 4416
    Prev
    Next
    INDEX
    Explanations

    mathematical structures involving arrays or matrices

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

    LaTeX array environments

    np_acts-logits-general · gemini-2.0-flash

    LaTeX array alignments

    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
    bootstrapcdn
    -0.90
    StructEnd
    -0.85
    AsUp
    -0.84
    Vidite
    -0.78
     ligiloj
    -0.77
    OGND
    -0.77
    IsContent
    -0.76
    Abitanti
    -0.76
    AndEndTag
    -0.74
    FunctionFlags
    -0.74
    POSITIVE LOGITS
    l
    0.46
    }{|
    0.44
     اش
    0.43
    ral
    0.42
    alu
    0.41
     Потому
    0.40
     Speise
    0.39
    延伸閱讀
    0.39
     ľ
    0.38
    どこ
    0.38
    Activations Density 0.011%

    No Known Activations