© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 325
    Prev
    Next
    INDEX
    Explanations

    aspects related to software and programming structures or commands

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

    after "a" or "Eclipse"

    np_acts-logits-general · gemini-2.0-flash

    custom settings

    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
    uxxxx
    -0.95
    sizeCache
    -0.76
    Datuak
    -0.76
    AddTagHelper
    -0.75
     métallique
    -0.73
    IndentedString
    -0.70
    findpost
    -0.70
     <>",
    -0.69
    الدراسه
    -0.69
     enfans
    -0.66
    POSITIVE LOGITS
     custom
    1.25
     Custom
    1.02
    custom
    0.92
    Custom
    0.89
     customized
    0.86
     customised
    0.80
    自定义
    0.79
     CUSTOM
    0.77
    カスタム
    0.70
     customizing
    0.69
    Activations Density 0.828%

    No Known Activations