© 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. 0-GEMMASCOPE-RES-16K
    6. 8981
    Prev
    Next
    INDEX
    Explanations

    references to managerial roles or responsibilities within a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.70
    ronique
    -0.57
    ThroughAttribute
    -0.55
    KommentareTeilen
    -0.55
     nemlig
    -0.54
    istock
    -0.53
     CreateTagHelper
    -0.52
    parsedMessage
    -0.49
    Хьажоргаш
    -0.49
    Havolalar
    -0.48
    POSITIVE LOGITS
    Manager
    1.06
     Manager
    1.05
     MANAGER
    1.01
    manager
    1.00
     Legs
    0.99
     Arms
    0.97
     ARMS
    0.96
     arms
    0.96
     legs
    0.90
     jambe
    0.90
    Activations Density 0.101%

    No Known Activations