Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5510
    Prev
    Next
    INDEX
    Explanations

    database-related commands and tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.78
     estimés
    -0.76
    Tikang
    -0.74
     pinulongan
    -0.67
     trajets
    -0.61
     ddelweddau
    -0.56
    InstrumentedTest
    -0.55
    WebVitals
    -0.55
     ostavi
    -0.53
     pylab
    -0.53
    POSITIVE LOGITS
     विश्वसनीयता
    0.98
    mybatisplus
    0.95
    CodedInputStream
    0.71
     AspNetCore
    0.70
    könyv
    0.69
    באנגלית
    0.66
    тябрь
    0.65
    っこう
    0.64
    UnsafeEnabled
    0.64
    WarningLevel
    0.62
    Activations Density 2.777%

    No Known Activations