© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28855
    Prev
    Next
    INDEX
    Explanations

    occurrences of unique identifiers and parameters in programming or data structures

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

    u8, STAT, GH, OS

    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
    ⓧ
    -1.00
    ItemBackground
    -0.76
    <?
    -0.73
    脚注の使い方
    -0.71
     MessageBoxIcon
    -0.70
     nahilalakip
    -0.69
     BorderRadius
    -0.64
    তথ্যসূত্র
    -0.63
    RUnlock
    -0.63
     ListTile
    -0.62
    POSITIVE LOGITS
    1
    1.16
    2
    1.16
    3
    0.99
     
    0.92
    4
    0.84
    6
    0.80
    5
    0.78
    7
    0.77
    9
    0.76
    8
    0.73
    Activations Density 2.406%

    No Known Activations