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. 20-GEMMASCOPE-RES-16K
    6. 5255
    Prev
    Next
    INDEX
    Explanations

    references to planning and organizational tools or features

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

    Task management and organization

    np_acts-logits-general · gemini-2.0-flash

    todo list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localctx
    -0.81
    出版年
    -0.74
    gameserver
    -0.70
    imageio
    -0.68
    RefNanny
    -0.67
    脚注の使い方
    -0.66
     Ouverture
    -0.64
    GEBURTSDATUM
    -0.64
    ंदीखरीदारी
    -0.62
    DebuggerStep
    -0.60
    POSITIVE LOGITS
     task
    1.14
     tasks
    1.10
     Task
    1.06
    Task
    1.05
     Tasks
    1.01
    task
    0.97
    Tasks
    0.94
    TaskList
    0.89
     Todo
    0.89
    tasks
    0.88
    Activations Density 0.218%

    No Known Activations