© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1198
    Prev
    Next
    INDEX
    Explanations

    technical terminology and attributes related to data storage systems and configurations

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

    Disk partitions or storage allocation

    np_acts-logits-general · gemini-2.0-flash

    disk partitioning

    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
     Exactos
    -0.60
     становника
    -0.59
    انجليز
    -0.55
    textTheme
    -0.53
    ensement
    -0.51
    mandu
    -0.51
    subequations
    -0.51
     Slaughter
    -0.50
    estinal
    -0.50
    StoreMessageInfo
    -0.50
    POSITIVE LOGITS
     storage
    1.01
     Storage
    0.95
    storage
    0.89
    Storage
    0.85
     disk
    0.83
     STORAGE
    0.82
    STORAGE
    0.76
    disk
    0.74
     Disk
    0.74
     almacenamiento
    0.72
    Activations Density 0.830%

    No Known Activations