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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11717
    Prev
    Next
    INDEX
    Explanations

    elements related to inventions and technological components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.50
     emp
    -0.36
     rest
    -0.35
    cepan
    -0.35
    тім
    -0.35
    Werdegang
    -0.35
    نجی
    -0.35
    David
    -0.34
     partners
    -0.34
    andidate
    -0.33
    POSITIVE LOGITS
     sekaligus
    0.90
     simultaneously
    0.87
     zugleich
    0.79
     одновременно
    0.77
     gleichzeitig
    0.73
     Simultaneously
    0.73
    simult
    0.72
     simultaneous
    0.69
     concurrently
    0.68
     zároveň
    0.67
    Activations Density 0.722%

    No Known Activations