© 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. 2076
    Prev
    Next
    INDEX
    Explanations

    references or identifiers within structured data

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

    Numbers separated by colons and curly braces

    np_acts-logits-general · gemini-2.0-flash

    fields and columns

    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
     the
    -0.52
    ,
    -0.51
     and
    -0.45
     an
    -0.44
     désolés
    -0.44
    .
    -0.43
     sich
    -0.43
     G
    -0.43
     F
    -0.42
    ází
    -0.42
    POSITIVE LOGITS
    RenderAtEndOf
    1.21
    ReusableCell
    1.17
    ValueStyle
    0.98
     typelib
    0.98
    Rhestr
    0.94
    ChildScrollView
    0.94
    >{@
    0.91
    IntoConstraints
    0.89
     مشين
    0.89
     autorytatywna
    0.89
    Activations Density 0.619%

    No Known Activations