© 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. 16-GEMMASCOPE-RES-16K
    11. 16375
    Prev
    Next
    INDEX
    Explanations

    structured instructions or steps in a process

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

    Instructions for software or operating systems

    np_acts-logits-general · gemini-2.0-flash

    completion or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagLayout
    -0.41
    LayoutStyle
    -0.39
     plan
    -0.37
    SetFont
    -0.37
    Nonnull
    -0.35
     mutual
    -0.35
     imageNamed
    -0.35
     daher
    -0.35
    הם
    -0.35
     Plan
    -0.34
    POSITIVE LOGITS
     voila
    1.05
    setVerticalGroup
    0.92
     Alternatively
    0.87
    Voila
    0.87
    Alternatively
    0.85
     voilà
    0.84
     presto
    0.83
    ConstraintMaker
    0.76
     tada
    0.76
     Voilà
    0.75
    Activations Density 0.279%

    No Known Activations