© 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. 7351
    Prev
    Next
    INDEX
    Explanations

    elements related to necessary but unexciting tasks

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

    Text following colons or commas

    np_acts-logits-general · gemini-2.0-flash

    methodical and precise descriptions

    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
     softer
    -0.55
     soften
    -0.54
     Soft
    -0.54
    SOFT
    -0.53
     Spontaneous
    -0.51
    Soft
    -0.51
    软
    -0.51
     softness
    -0.51
     surla
    -0.50
     软
    -0.50
    POSITIVE LOGITS
     boring
    0.85
     froide
    0.84
     impersonal
    0.81
     austere
    0.79
     monotonous
    0.79
    boring
    0.78
     methodical
    0.78
     Boring
    0.78
     exac
    0.76
    Boring
    0.75
    Activations Density 0.413%

    No Known Activations