© 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. 20-GEMMASCOPE-RES-16K
    11. 2557
    Prev
    Next
    INDEX
    Explanations

    references to user instructions and personalization in guidance

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

    Precedes "want" or "would like"

    np_acts-logits-general · gemini-2.0-flash

    expressing desire or lack of desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensement
    -0.64
    WriteAttribute
    -0.47
     AssemblyCulture
    -0.45
    NullException
    -0.45
    ftagPool
    -0.43
    )]:
    -0.42
     flywheel
    -0.41
    čin
    -0.41
    toplas
    -0.41
     AssemblyCompany
    -0.41
    POSITIVE LOGITS
     want
    3.16
     wants
    2.84
    want
    2.81
     Want
    2.71
     wanting
    2.70
     wanted
    2.65
    Want
    2.48
    wants
    2.32
     desire
    2.31
     WANT
    2.29
    Activations Density 1.170%

    No Known Activations