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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 150
    Prev
    Next
    INDEX
    Explanations

    concepts and terminology related to flow and flowcharts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    -1.08
     fubject
    -1.06
     pleaſure
    -1.03
     greateſt
    -1.01
     Chriftian
    -1.01
     Jefus
    -1.00
     Monfieur
    -0.99
     purpoſe
    -0.94
     preſent
    -0.94
     myſelf
    -0.93
    POSITIVE LOGITS
     flow
    2.98
     Flow
    2.88
    flow
    2.77
    Flow
    2.69
     flows
    2.58
     FLOW
    2.53
    FLOW
    2.37
     Flows
    2.27
    flows
    2.18
    Flows
    2.13
    Activations Density 0.043%

    No Known Activations