© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28447
    Prev
    Next
    INDEX
    Explanations

    symbols representing links or references, particularly in data or code contexts

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

    code and commands

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Efq
    -0.85
     Frick
    -0.81
     Anſ
    -0.80
     crdi
    -0.79
     themſelves
    -0.77
     Majefty
    -0.75
     Pallas
    -0.75
     Herd
    -0.74
     himſelf
    -0.74
    Pranala
    -0.74
    POSITIVE LOGITS
    ing
    1.47
    ING
    1.09
    ة
    1.00
    いる
    0.94
    ی
    0.91
    evo
    0.87
     Bowden
    0.82
    iya
    0.81
    ingan
    0.81
    tling
    0.80
    Activations Density 0.026%

    No Known Activations