© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4188
    Prev
    Next
    INDEX
    Explanations

    mention of server capacity and resource management in the context of scaling and load balancing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.61
     isolato
    -0.60
     Olympedia
    -0.60
    ActivityCompat
    -0.58
     Shakspeare
    -0.57
    hyrchwyd
    -0.55
     paziente
    -0.55
     Efq
    -0.54
     pareti
    -0.53
    Autoritní
    -0.52
    POSITIVE LOGITS
     capacity
    0.88
     Capacity
    0.79
    capacity
    0.74
    AddTagHelper
    0.72
    kháu
    0.70
     CAPACITY
    0.69
     capacities
    0.67
     overcrowding
    0.66
     demand
    0.64
     capac
    0.63
    Activations Density 0.304%

    No Known Activations