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. 5-GEMMASCOPE-RES-16K
    6. 3639
    Prev
    Next
    INDEX
    Explanations

    phrases related to commitment and dedication to a cause or service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.79
     الدولى
    -0.66
    yordu
    -0.57
     Diplomacy
    -0.55
     sospe
    -0.54
     uby
    -0.54
     officiers
    -0.54
     Ouv
    -0.53
    InputBorder
    -0.53
     tibet
    -0.53
    POSITIVE LOGITS
     commitment
    0.92
     Commitment
    0.88
    commitment
    0.82
     committed
    0.82
     propOrder
    0.81
    Commitment
    0.78
    committed
    0.78
     Committed
    0.76
     COMMIT
    0.76
     pursuit
    0.75
    Activations Density 0.164%

    No Known Activations