© 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. 18-GEMMASCOPE-RES-16K
    11. 4233
    Prev
    Next
    INDEX
    Explanations

    numerical data and technical terminology related to software or application integration

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

    Numbers followed by specific letters

    np_acts-logits-general · gemini-2.0-flash

    identifiers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -1.01
     незавершена
    -1.00
    richTextPanel
    -0.88
    :✨
    -0.88
    Personensuche
    -0.87
    mybatisplus
    -0.86
    
    -0.85
     <<<<<<<<<<<<<<
    -0.82
     autorytatywna
    -0.81
    InjectAttribute
    -0.81
    POSITIVE LOGITS
    createObject
    0.55
    .
    0.46
    3
    0.44
    ?
    0.43
    方で
    0.42
     
    0.38
    0
    0.38
    7
    0.38
     Fac
    0.38
    かを
    0.38
    Activations Density 0.135%

    No Known Activations