© 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. 16171
    Prev
    Next
    INDEX
    Explanations

    programming-related terminators and flow control keywords

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

    "end" keyword, including variations in capitalization

    np_acts-logits-general · gemini-2.0-flash

    end of code blocks

    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
     ItemStack
    -0.65
    neté
    -0.56
    justed
    -0.56
    jsonwebtoken
    -0.55
     AssemblyCulture
    -0.54
    nocache
    -0.54
    __(/*!
    -0.54
    ModelAdmin
    -0.53
    NullException
    -0.53
     aquilo
    -0.53
    POSITIVE LOGITS
     End
    0.57
    脚注の使い方
    0.53
    rceil
    0.51
    WriteTagHelper
    0.50
    Lähteet
    0.50
     مفت
    0.49
     defStyleAttr
    0.49
     Eind
    0.49
     watching
    0.47
    μός
    0.47
    Activations Density 0.168%

    No Known Activations