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. 230
    Prev
    Next
    INDEX
    Explanations

    references to specific tasks and their management

    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
     transparencia
    -0.54
     vermelhas
    -0.52
     exportaciones
    -0.49
     tertutup
    -0.48
     vermelha
    -0.48
     financiero
    -0.47
     EconPapers
    -0.47
     meille
    -0.46
     vermelho
    -0.46
     pieles
    -0.46
    POSITIVE LOGITS
     Task
    1.45
     task
    1.39
     Tasks
    1.35
     tasks
    1.34
    Task
    1.31
     TASK
    1.27
    task
    1.20
    TASK
    1.16
    tasks
    1.16
    Tasks
    1.16
    Activations Density 0.111%

    No Known Activations