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. 16-GEMMASCOPE-RES-16K
    6. 6475
    Prev
    Next
    INDEX
    Explanations

    references to artificial intelligence and its applications

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

    "AI", "algorithms", and related terms

    np_acts-logits-general · gemini-2.0-flash

    AI and algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lượt
    -0.62
    ieteur
    -0.53
     htons
    -0.50
     příslu
    -0.49
     inconvenient
    -0.49
     comunit
    -0.49
    Péri
    -0.48
    BorderLayout
    -0.48
     okaz
    -0.48
    ModelAdmin
    -0.48
    POSITIVE LOGITS
     automated
    0.95
     AI
    0.91
     Artificial
    0.90
     automat
    0.82
     robot
    0.82
     Automated
    0.80
    automated
    0.80
     automatic
    0.79
    🤖
    0.78
    Artificial
    0.78
    Activations Density 0.370%

    No Known Activations