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. 22-GEMMASCOPE-RES-16K
    6. 13837
    Prev
    Next
    INDEX
    Explanations

    terms and constructs related to graph traversal algorithms, particularly breadth-first search (BFS)

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

    Code related to queues and stacks

    np_acts-logits-general · gemini-2.0-flash

    queue operations and stack appends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.58
     Shooter
    -0.57
    ValueStyle
    -0.56
    DockStyle
    -0.54
     concerto
    -0.53
     BoxDecoration
    -0.53
     Shooting
    -0.52
    Shooting
    -0.52
    편
    -0.52
     numberWith
    -0.52
    POSITIVE LOGITS
     queue
    1.05
    queue
    1.05
    Queue
    1.04
     Queue
    0.95
     priority
    0.91
     stack
    0.88
    priority
    0.86
    Stack
    0.81
    QUEUE
    0.81
     Priority
    0.80
    Activations Density 0.122%

    No Known Activations