© 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. 8562
    Prev
    Next
    INDEX
    Explanations

    terms related to testing and quality assurance processes

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

    ending in "ing" or "tion"

    np_acts-logits-general · gemini-2.0-flash

    gerunds and participles

    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
    setopt
    -0.93
    InstanceState
    -0.87
     getRule
    -0.82
     flesta
    -0.78
     Ruh
    -0.72
    ্ন
    -0.68
    égard
    -0.67
    icef
    -0.66
    hommes
    -0.66
    ไหน
    -0.65
    POSITIVE LOGITS
    ging
    0.99
    ting
    0.95
    gggg
    0.93
    ding
    0.92
    ning
    0.91
    izing
    0.89
    ating
    0.86
    NING
    0.84
    Kariera
    0.83
    zing
    0.83
    Activations Density 0.776%

    No Known Activations