© 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. 4201
    Prev
    Next
    INDEX
    Explanations

    structured mathematical expressions and formatting elements used in equations

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

    Code within mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    gathered

    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
    openConnection
    -0.54
    <eos>
    -0.49
     الع
    -0.41
     Kirk
    -0.39
    okhttp
    -0.39
    รก
    -0.38
    Unmarshal
    -0.38
    rp
    -0.38
    oush
    -0.38
    در
    -0.37
    POSITIVE LOGITS
    :✨
    0.84
     للاسماء
    0.84
    Personensuche
    0.82
    ✨:
    0.78
     AssemblyCulture
    0.76
     Савезне
    0.76
     للمعارف
    0.75
     autorytatywna
    0.75
    PostExecute
    0.73
    цездатний
    0.71
    Activations Density 0.015%

    No Known Activations