© 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. 5677
    Prev
    Next
    INDEX
    Explanations

    terms related to comparative or superlative qualities

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

    "higher" followed by a measurable quantity

    np_acts-logits-general · gemini-2.0-flash

    higher degree or quantity

    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
     ramai
    -0.53
     prostředí
    -0.50
    AnchorStyles
    -0.48
     mús
    -0.47
    pores
    -0.46
     fatica
    -0.46
    qtype
    -0.45
     přístup
    -0.44
    ClassNotFound
    -0.44
     pikir
    -0.44
    POSITIVE LOGITS
     levels
    0.93
     level
    0.93
    IntoConstraints
    0.83
     ranking
    0.81
    WriteAttribute
    0.79
     ranked
    0.76
     degree
    0.76
     octane
    0.76
     priced
    0.74
    WriteTagHelper
    0.73
    Activations Density 0.183%

    No Known Activations